© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210096
    Prev
    Next
    INDEX
    Explanations

    you followed by action

    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_10_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
    fastq
    0.29
    ض
    0.27
    حب
    0.27
    веря
    0.27
    ول
    0.27
    獐
    0.26
     reorgan
    0.26
    濩
    0.26
    ون
    0.25
    ü
    0.25
    POSITIVE LOGITS
    2
    0.33
    D
    0.28
    )}
    0.28
    s
    0.27
    3
    0.26
    6
    0.26
     ז
    0.25
     kullan
    0.25
    4
    0.25
     has
    0.25
    Activations Density 0.020%

    No Known Activations