© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162084
    Prev
    Next
    INDEX
    Explanations

    keratosis pilaris

    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_2_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
    ן
    1.23
    <0x0D>
    1.18
    ки
    1.13
    I
    1.08
    ंना
    1.07
     casque
    1.06
     рада
    1.02
     که
    1.02
    ка
    1.01
    که
    1.00
    POSITIVE LOGITS
    e
    1.32
    ak
    1.29
    c
    1.29
     it
    1.26
    ض
    1.21
    al
    1.19
    ig
    1.19
    ek
    1.19
    em
    1.16
    un
    1.15
    Activations Density 0.001%

    No Known Activations