© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12825
    Prev
    Next
    INDEX
    Explanations

    legal documents with associated names

    oai_token-act-pair · gemini-2.0-flash

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ModelExpression
    -0.81
    StructEnd
    -0.77
     oprot
    -0.75
    tvguidetime
    -0.75
    Datuak
    -0.75
     AssemblyVersion
    -0.74
     resourceCulture
    -0.71
    ValueGeneration
    -0.70
     useAppContext
    -0.70
    GraphicsUnit
    -0.70
    POSITIVE LOGITS
    glTexCoord
    0.53
    gebracht
    0.47
    tari
    0.45
     off
    0.44
    اريخ
    0.44
     them
    0.43
     any
    0.42
    มาย
    0.42
     total
    0.41
    laris
    0.41
    Activations Density 2.367%

    No Known Activations