© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12762
    Prev
    Next
    INDEX
    Explanations

    the year 2020 or 202X

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    UserScript
    -0.61
    BuildContext
    -0.56
    NameInMap
    -0.50
    <bos>
    -0.50
    bkz
    -0.47
    帖最后由
    -0.47
    CopyWith
    -0.46
     sixth
    -0.45
    SPATH
    -0.45
     six
    -0.43
    POSITIVE LOGITS
    1
    0.60
    0
    0.59
    ArgsConstructor
    0.58
     Normdatei
    0.57
    enumi
    0.56
     tartalomajánló
    0.54
    万美元
    0.54
    AutoSize
    0.53
     alike
    0.52
     Trials
    0.51
    Activations Density 2.383%

    No Known Activations