© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 730
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols, as well as some related terms like "survive", "prosper", or "etc"

    oai_token-act-pair · gemini-2.0-flash

    say "end with parenthesis )"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ";
    -0.71
    ",
    -0.59
    ".
    -0.56
    спу
    -0.54
    chal
    -0.54
     Loaf
    -0.54
    cuma
    -0.54
    CÓ
    -0.54
     Acta
    -0.53
    feit
    -0.53
    POSITIVE LOGITS
    $
    1.34
    ruptedException
    0.59
    Autoritní
    0.57
    CodeAttribute
    0.56
     concorso
    0.56
    tagext
    0.56
    }$
    0.55
     purpoſe
    0.54
    @[+][
    0.53
    URLException
    0.50
    Activations Density 3.935%

    No Known Activations