© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2587
    Prev
    Next
    INDEX
    Explanations

    mentions of interconnectedness, relationship, or separation between ideas.

    oai_token-act-pair · gemini-2.0-flash

    themes related to society and existence

    np_token-act-pair-logits · gpt-4o-mini

    perceive and respond to reality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BufferedReader
    -0.52
    AsUp
    -0.49
    ariest
    -0.48
    audiovisuel
    -0.47
     Raising
    -0.46
     bParam
    -0.46
     onOptions
    -0.45
    IsContent
    -0.45
     Trigon
    -0.44
    цезда
    -0.44
    POSITIVE LOGITS
    tiqueta
    0.57
     humanity
    0.57
    ividual
    0.56
     society
    0.55
     something
    0.54
     assumptions
    0.54
    ();)
    0.53
     caufe
    0.52
    ünkü
    0.52
     symbols
    0.52
    Activations Density 7.599%

    No Known Activations