© 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. 2986
    Prev
    Next
    INDEX
    Explanations

    seemingly random hexadecimal strings and the word "Od".

    oai_token-act-pair · gemini-2.0-flash

    Od

    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
    новниш
    -0.81
    ians
    -0.78
    dles
    -0.71
    клопе
    -0.69
    iate
    -0.69
     useAppContext
    -0.68
    dine
    -0.68
    tiness
    -0.65
    ]$}
    -0.64
    esign
    -0.63
    POSITIVE LOGITS
    n
    0.50
    g
    0.43
    od
    0.41
    Named
    0.40
    gulan
    0.39
     dormitorios
    0.38
     Sonn
    0.38
    FloatField
    0.38
    end
    0.36
    ap
    0.36
    Activations Density 0.431%

    No Known Activations