© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199286
    Prev
    Next
    INDEX
    Explanations

    later, subsequent actions

    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_9_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
    <0x0D>
    0.54
    enciado
    0.47
    ᅥ
    0.47
     sep
    0.47
     alerg
    0.46
    ح
    0.44
    lação
    0.44
     श्रीलंका
    0.43
     poten
    0.43
    ة
    0.43
    POSITIVE LOGITS
     дальнейшем
    0.47
     بعدی
    0.47
    경제
    0.47
     دیتے
    0.46
    iw
    0.46
     موسی
    0.44
    inib
    0.44
     ಇನ್ನ
    0.43
    เคร
    0.43
     થશે
    0.43
    Activations Density 0.000%

    No Known Activations