© 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. 1107
    Prev
    Next
    INDEX
    Explanations

    text in all caps, especially when followed by words related to instructions or actions

    oai_token-act-pair · gemini-2.0-flash

    instructions, requests, requirements

    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
    DockStyle
    -0.76
     createState
    -0.74
    ConstraintMaker
    -0.73
    posedge
    -0.65
     Chwiliwch
    -0.64
     الدولى
    -0.63
    AntiForgeryToken
    -0.60
     intervene
    -0.60
    extAlignment
    -0.60
    expandindo
    -0.59
    POSITIVE LOGITS
     Turquie
    0.54
    ENTA
    0.46
    ALLOW
    0.46
    >>()
    0.46
    Angleterre
    0.45
     SEND
    0.44
    USE
    0.44
    Marca
    0.42
    Климат
    0.41
    USET
    0.41
    Activations Density 1.795%

    No Known Activations