© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6791
    Prev
    Next
    INDEX
    Explanations

    instances of needing something

    oai_token-act-pair · gemini-2.0-flash

    need

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AutoresizingMask
    -0.80
    TestingModule
    -0.64
    #+#
    -0.59
    WEBPACK
    -0.59
    DoubleQuotes
    -0.57
    Personendaten
    -0.57
    interopRequire
    -0.57
    setViewportView
    -0.56
    FunctionFlags
    -0.53
      (
    -0.50
    POSITIVE LOGITS
     to
    0.75
    to
    0.66
    lismo
    0.60
     vnto
    0.53
    expandindo
    0.52
    lceil
    0.52
     biogas
    0.50
    toed
    0.50
     saluted
    0.49
     treated
    0.48
    Activations Density 10.374%

    No Known Activations