© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6281
    Prev
    Next
    INDEX
    Explanations

    text about health initiatives and helping people

    oai_token-act-pair · gemini-2.0-flash

    words related to heritage or legacy

    np_token-act-pair-logits · gpt-4o-mini

    Organizations and support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     bit
    -0.85
     Bit
    -0.80
     Bits
    -0.79
    LookAnd
    -0.78
    CPtr
    -0.77
     bits
    -0.75
    TintMode
    -0.72
     مشين
    -0.71
     doInBackground
    -0.71
    EndInit
    -0.68
    POSITIVE LOGITS
     szint
    0.50
     cela
    0.47
     nasled
    0.44
     beziehen
    0.43
     colectivos
    0.42
     gruppi
    0.41
     velik
    0.40
     meman
    0.40
     rodo
    0.40
    遺産
    0.40
    Activations Density 1.041%

    No Known Activations