© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12619
    Prev
    Next
    INDEX
    Explanations

    text from log files and code snippets or referring to links and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    Internet/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    </strong>
    -0.53
    </blockquote>
    -0.51
    </h3>
    -0.45
    </b>
    -0.43
     oxidizing
    -0.42
    ↵↵
    -0.42
    </h2>
    -0.42
     sulphide
    -0.42
    ↵↵↵↵
    -0.41
    </h5>
    -0.41
    POSITIVE LOGITS
    okovic
    0.66
     vuitton
    0.66
    XmlEnum
    0.65
     Normdatei
    0.63
    PYX
    0.62
    ngths
    0.60
    inafter
    0.58
    ˛
    0.58
    Identyfik
    0.58
    bir
    0.57
    Activations Density 57.445%

    No Known Activations