© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141583
    Prev
    Next
    INDEX
    Explanations

    bleeding, scrapes, peeling skin

    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_12_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
     bruises
    0.76
     bruising
    0.72
     bruise
    0.66
     和
    0.62
    一场
    0.60
    ために
    0.59
     bruised
    0.59
    ोब
    0.57
    ска
    0.57
    también
    0.57
    POSITIVE LOGITS
    Songs
    0.57
    apan
    0.55
    ஷ்
    0.52
     Humph
    0.52
     garis
    0.51
    aviti
    0.48
    ktron
    0.48
     मश
    0.47
     औ
    0.46
    âtre
    0.46
    Activations Density 0.008%

    No Known Activations