© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14785
    Prev
    Next
    INDEX
    Explanations

    questions that have been or will be considered

    oai_token-act-pair · gemini-2.0-flash

    discussing/resolving issues

    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
    parsedMessage
    -0.71
     discussion
    -0.66
    InitVars
    -0.62
     discuss
    -0.60
     referenties
    -0.60
     dealt
    -0.56
     deal
    -0.55
    discussion
    -0.54
    "]];
    -0.54
     discussing
    -0.53
    POSITIVE LOGITS
    MockMvc
    0.56
    ConstraintMaker
    0.53
    SuppressLint
    0.53
    styleType
    0.52
    RoutingModule
    0.50
    FormTagHelper
    0.49
    UIControlState
    0.48
    SourceChecksum
    0.47
    itettura
    0.47
    isle
    0.46
    Activations Density 9.158%

    No Known Activations