© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157644
    Prev
    Next
    INDEX
    Explanations

    encyclopedias and AI

    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_50_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
     επο
    0.41
    replay
    0.39
    ශ
    0.38
    AI
    0.38
     diber
    0.37
    賞
    0.37
     স্থাপত্য
    0.37
    ộm
    0.37
     summons
    0.37
     சொல்
    0.36
    POSITIVE LOGITS
     Utt
    0.45
     jum
    0.43
     Lido
    0.43
     Jum
    0.42
    钯
    0.42
     P
    0.41
     palladium
    0.40
     Lid
    0.40
     LJ
    0.40
     Lili
    0.39
    Activations Density 0.000%

    No Known Activations