© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169734
    Prev
    Next
    INDEX
    Explanations

    body

    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_56_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
     ফর
    0.37
    Fifty
    0.36
    ocent
    0.36
     Fifty
    0.36
     >>>
    0.35
    ৈ
    0.35
    ;++
    0.35
     oblik
    0.35
    而不
    0.34
     ;
    0.34
    POSITIVE LOGITS
    дея
    0.35
     adjectives
    0.34
     asn
    0.34
    ວຍ
    0.33
     باتوں
    0.33
     chamado
    0.32
     Phrases
    0.32
     ಕೆಲ
    0.32
    គឺ
    0.32
    াহরণ
    0.32
    Activations Density 0.000%

    No Known Activations