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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102438
    Prev
    Next
    INDEX
    Explanations

    creating title/vocational names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]|
    0.49
    pmap
    0.46
     Willoughby
    0.46
    󠁢
    0.46
    <0x0D>
    0.44
    jdbcType
    0.44
    챱
    0.43
     goof
    0.43
    ordinal
    0.43
    сіння
    0.43
    POSITIVE LOGITS
    otros
    0.50
    Mis
    0.48
    న్
    0.47
    ί
    0.46
     защи
    0.46
    eração
    0.45
    ين
    0.44
    dan
    0.44
     ανάπτυ
    0.44
    se
    0.43
    Activations Density 0.000%

    No Known Activations