© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific codes used in biological experiments

    oai_token-act-pair · gemini-2.0-flash

    nucleotide sequences or chemical modifications

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

    hsiRNA experiments

    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
    FTFY
    -1.09
    — 
    -0.98
    AllAfrica
    -0.83
    ureka
    -0.78
     AttributeSet
    -0.78
    uests
    -0.76
    Numerade
    -0.75
     '{@
    -0.74
    NUMX
    -0.74
     onCreateView
    -0.73
    POSITIVE LOGITS
    V
    0.69
    NO
    0.68
    O
    0.67
    T
    0.67
    F
    0.66
    P
    0.66
    FC
    0.65
    X
    0.65
    U
    0.65
    Q
    0.64
    Activations Density 4.015%

    No Known Activations