© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35662
    Prev
    Next
    INDEX
    Explanations

    fulfill the prompt

    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_7_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
     publicar
    0.39
    ってます
    0.37
    <0x80>
    0.36
    だろう
    0.36
    ﾞ
    0.35
    Ꮦ
    0.35
    فظ
    0.34
    یل
    0.34
    ものを
    0.34
    ləşdir
    0.33
    POSITIVE LOGITS
     are
    0.64
    ка
    0.55
    and
    0.53
    in
    0.52
    un
    0.49
    та
    0.48
    ة
    0.47
    it
    0.47
    ar
    0.47
     as
    0.47
    Activations Density 0.003%

    No Known Activations