© 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. 14101
    Prev
    Next
    INDEX
    Explanations

    words which are prepositions, adjectives, or adverbs

    oai_token-act-pair · gemini-2.0-flash

    terms related to relationships

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

    Describing a situation

    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
    AndEndTag
    -0.51
    entyfik
    -0.48
     artinya
    -0.48
     OFDb
    -0.48
    FontOfSize
    -0.47
    omitempty
    -0.46
    сову
    -0.46
    anueva
    -0.45
    enumi
    -0.45
     Effekt
    -0.45
    POSITIVE LOGITS
     relative
    0.60
     виправивши
    0.59
    relative
    0.57
    tvguidetime
    0.57
     jScrollPane
    0.56
     continuous
    0.56
    plenty
    0.56
     heavy
    0.55
     fine
    0.55
     action
    0.54
    Activations Density 2.235%

    No Known Activations