© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    the word "of" by itself or in frequent phrases

    oai_token-act-pair · gemini-2.0-flash

    discussions, communities, opinions

    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
     and
    -0.88
     for
    -0.68
     to
    -0.59
    ']").
    -0.58
    "]),
    -0.57
    '}),
    -0.54
    "});
    -0.54
    .}\
    -0.54
     in
    -0.54
     a
    -0.54
    POSITIVE LOGITS
     defaultstate
    0.80
     Cæsar
    0.74
    OGND
    0.74
    apimachinery
    0.73
     BrowserModule
    0.72
     ModelExpression
    0.72
    scriptcase
    0.71
    PYX
    0.71
     AssemblyVersion
    0.70
    RectangleBorder
    0.69
    Activations Density 15.017%

    No Known Activations