© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54128
    Prev
    Next
    INDEX
    Explanations

    eye, skin, hair

    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_55_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
    ረ
    0.38
     Pressure
    0.38
    眽
    0.36
    avin
    0.35
    chtel
    0.35
     Wass
    0.35
     تربيع
    0.35
    
    0.34
    டனும்
    0.34
    ⎞
    0.34
    POSITIVE LOGITS
     eye
    1.44
     skin
    1.19
    Eye
    1.18
    eye
    1.16
     Eye
    1.15
     hair
    1.05
    Skin
    0.97
    skin
    0.96
     Skin
    0.93
     EYE
    0.91
    Activations Density 0.117%

    No Known Activations