© 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. 10516
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings

    oai_token-act-pair · gemini-2.0-flash

    Alphanumeric strings

    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
     nahilalakip
    -1.05
     <=",
    -1.01
    });*/
    -1.01
     Meksiku
    -0.99
     Italijanski
    -0.97
    ValueStyle
    -0.96
     Мексичка
    -0.95
     Efq
    -0.94
    HtmlAttribute
    -0.93
     ligiloj
    -0.93
    POSITIVE LOGITS
    j
    0.87
    0
    0.80
    /
    0.80
    v
    0.76
    1
    0.76
    4
    0.74
    3
    0.74
    c
    0.73
    b
    0.72
    d
    0.69
    Activations Density 8.650%

    No Known Activations