© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142098
    Prev
    Next
    INDEX
    Explanations

    hanger or hangar

    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_0_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
    1
    1.34
    ปี
    1.26
    ne
    1.25
    то
    1.23
    ka
    1.22
    中医
    1.21
    to
    1.16
    ed
    1.15
    に
    1.15
    国内
    1.13
    POSITIVE LOGITS
    ьте
    1.56
    :
    1.48
    та
    1.46
    س
    1.40
    וד
    1.34
    ะ
    1.30
    ם
    1.30
    э
    1.22
    ON
    1.16
    ></
    1.16
    Activations Density 0.000%

    No Known Activations