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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217970
    Prev
    Next
    INDEX
    Explanations

    booking travel services

    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_31_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
    FEED
    0.43
     Feed
    0.39
     Huo
    0.37
     FEED
    0.37
     ರಿ
    0.36
    cheduling
    0.35
    eOut
    0.35
    𝓶
    0.35
    喂
    0.35
     Mustang
    0.35
    POSITIVE LOGITS
     avec
    0.46
    กับ
    0.44
     със
    0.43
     معايا
    0.41
    avec
    0.40
     kanssa
    0.40
     with
    0.40
    ுடன்
    0.38
     dengan
    0.38
     עם
    0.38
    Activations Density 0.010%

    No Known Activations