© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    instances of helpful conditional language usually involving an offer

    oai_token-act-pair · gemini-2.0-flash

    Requests and offers

    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
     free
    -0.57
     Free
    -0.54
    RenderAtEndOf
    -0.53
     biologique
    -0.50
     files
    -0.50
    Free
    -0.50
    UnknownFields
    -0.49
    nutie
    -0.49
     jsPsych
    -0.48
    معلومات
    -0.47
    POSITIVE LOGITS
    IndentedString
    0.81
    StoryboardSegue
    0.64
    хь
    0.55
    ForRow
    0.55
     समीक्षाएं
    0.54
     Ven
    0.51
    intele
    0.51
    axter
    0.51
    colgroup
    0.50
    FormatException
    0.50
    Activations Density 5.830%

    No Known Activations