© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179467
    Prev
    Next
    INDEX
    Explanations

    explanation or question

    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_24_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
     combiner
    0.48
     finisher
    0.47
     uploaded
    0.45
     is
    0.45
    al
    0.45
     shared
    0.45
     rejoindre
    0.44
    챕
    0.44
     পুনরায়
    0.44
    잼
    0.43
    POSITIVE LOGITS
    대는
    0.46
    '،
    0.46
     режим
    0.46
    have
    0.45
     hapless
    0.45
     bhavanti
    0.44
    とおり
    0.43
     Гра
    0.43
    ферен
    0.43
     apakah
    0.42
    Activations Density 0.000%

    No Known Activations