© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5894
    Prev
    Next
    INDEX
    Explanations

    programming data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     immisc
    0.18
     😉
    0.17
     nmea
    0.17
     hva
    0.17
    鏃
    0.17
     কিল
    0.16
     неза
    0.16
    Ს
    0.16
    热爱
    0.16
    惬
    0.16
    POSITIVE LOGITS
     исключением
    0.15
    ?[
    0.15
    Ra
    0.15
    ehle
    0.14
     Ra
    0.14
     নীতি
    0.14
     Examine
    0.14
    ?:
    0.14
    Anim
    0.14
    நீ
    0.14
    Activations Density 0.441%

    No Known Activations