© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8749
    Prev
    Next
    INDEX
    Explanations

    mentions of the prefix "Mal"

    oai_token-act-pair · gemini-2.0-flash

    Mal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ProtoMessage
    -0.72
    offsetof
    -0.69
     CWE
    -0.66
     Numerade
    -0.65
    ftagPool
    -0.65
     ITIS
    -0.63
    ScopeManager
    -0.63
    GraphicsUnit
    -0.63
     hoi
    -0.63
    intios
    -0.63
    POSITIVE LOGITS
    krieg
    0.46
    ia
    0.44
    ArrowToggle
    0.42
    atleta
    0.40
    ib
    0.40
    ig
    0.39
     acrílico
    0.38
    iba
    0.38
    pedes
    0.37
    ice
    0.37
    Activations Density 0.705%

    No Known Activations