© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    technical writing in the domain of physics

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with "▁" or specific prefixes

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

    optical physics

    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
     насељу
    -0.91
    HasAnnotation
    -0.84
    fjspx
    -0.84
     الرياضيه
    -0.82
     ISNI
    -0.80
     linkovi
    -0.80
    tanleria
    -0.79
    featureID
    -0.79
    msgTypes
    -0.79
     lenker
    -0.78
    POSITIVE LOGITS
     mode
    0.46
     base
    0.42
     ط
    0.41
    agua
    0.41
     ent
    0.40
    ent
    0.40
     mind
    0.39
     bun
    0.39
     Mel
    0.39
    ents
    0.38
    Activations Density 3.497%

    No Known Activations