© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10476
    Prev
    Next
    INDEX
    Explanations

    instances of someone doing as much as they can

    oai_token-act-pair · gemini-2.0-flash

    Expressing ability and possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     surla
    -1.09
    LookAnd
    -1.03
    .*")]
    -0.93
    RectangleBorder
    -0.91
     GenerationType
    -0.91
    AndEndTag
    -0.90
    findpost
    -0.89
     nahilalakip
    -0.89
    };*/
    -0.88
    
    -0.88
    POSITIVE LOGITS
     can
    0.67
    can
    0.58
    com
    0.54
    —
    0.51
    Can
    0.48
    <eos>
    0.47
    A
    0.47
    age
    0.46
    ages
    0.45
    in
    0.44
    Activations Density 0.931%

    No Known Activations