© 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. 164687
    Prev
    Next
    INDEX
    Explanations

    in a context

    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
     tormented
    0.37
    നിന്ന്
    0.37
    numerator
    0.36
     cram
    0.35
     eneste
    0.35
     }//
    0.34
     haunt
    0.33
    numOf
    0.33
    тической
    0.33
     när
    0.33
    POSITIVE LOGITS
     \{
    0.40
    君
    0.38
    शिता
    0.36
     Chiefs
    0.36
     delegation
    0.36
    皺
    0.36
     ক্ষত্রিয়
    0.36
     brakes
    0.35
     cavitation
    0.35
     extrusion
    0.34
    Activations Density 0.001%

    No Known Activations