© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14107
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to requirements needed to satisfy some requirement or achieve some goal

    oai_token-act-pair · gemini-2.0-flash

    requirement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Portale
    -0.74
    ArrowToggle
    -0.73
     alimentaire
    -0.69
     jsPsych
    -0.68
     createSprite
    -0.68
     onPostExecute
    -0.67
    Cyfeiriadau
    -0.66
     utafitiHapana
    -0.66
     AssemblyVersion
    -0.66
     BoxFit
    -0.65
    POSITIVE LOGITS
    <bos>
    0.69
     that
    0.47
     you
    0.45
     bet
    0.44
     who
    0.44
     is
    0.43
     he
    0.42
    ondissement
    0.42
     won
    0.42
     don
    0.41
    Activations Density 2.149%

    No Known Activations