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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11502
    Prev
    Next
    INDEX
    Explanations

    the usage of pronouns in relation to some action or time

    oai_token-act-pair · gemini-2.0-flash

    availability words

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

    free / available

    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
    =$?
    -0.75
     تانيه
    -0.70
     snippetHide
    -0.61
    awaiter
    -0.61
    ANTAGES
    -0.60
    GeoNames
    -0.59
    σιμοποι
    -0.59
     pleaſure
    -0.58
    Diweddarwch
    -0.58
     IBRARY
    -0.57
    POSITIVE LOGITS
     free
    0.79
    free
    0.66
     libres
    0.60
     available
    0.59
     Free
    0.59
    Free
    0.58
     liberi
    0.57
    AVAILABLE
    0.54
     FREE
    0.52
     Available
    0.52
    Activations Density 0.969%

    No Known Activations