© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89351
    Prev
    Next
    INDEX
    Explanations

    some cases

    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_23_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
     fees
    0.38
    fees
    0.37
    boton
    0.35
     FEES
    0.31
     reset
    0.31
     Fees
    0.30
    [-\
    0.30
    国外
    0.30
    )["
    0.30
    েন্ত্র
    0.30
    POSITIVE LOGITS
    কিন্তু
    0.41
     आह
    0.37
     তাই
    0.36
     فاط
    0.36
    FACT
    0.35
     Auch
    0.35
    Auch
    0.35
    عي
    0.35
     UHD
    0.35
     ziy
    0.35
    Activations Density 0.003%

    No Known Activations