© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244325
    Prev
    Next
    INDEX
    Explanations

    claims and allegations

    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_40_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
     indépend
    0.39
     отка
    0.39
     independently
    0.38
     diretamente
    0.38
    }}$-
    0.38
    itek
    0.38
    }}}=
    0.38
     direttamente
    0.38
     directamente
    0.37
    epend
    0.37
    POSITIVE LOGITS
     Meesho
    0.39
    筏
    0.38
     Kitt
    0.37
    блон
    0.36
    ᇁ
    0.36
    About
    0.35
    Nama
    0.35
     کشمیر
    0.35
     attributes
    0.34
     عن
    0.34
    Activations Density 0.000%

    No Known Activations