© 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. 180173
    Prev
    Next
    INDEX
    Explanations

    randomly generated

    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
     bác
    0.46
     আসে
    0.44
    ína
    0.44
    班牙
    0.43
    essentially
    0.43
     frá
    0.43
    acos
    0.42
    ³
    0.42
    阌
    0.42
    ние
    0.41
    POSITIVE LOGITS
     According
    0.52
     accords
    0.50
    ر
    0.49
     VAC
    0.48
    ற்றும்
    0.47
     Animated
    0.46
     ACHIE
    0.46
     Enlarg
    0.46
     Irishman
    0.46
     Anch
    0.46
    Activations Density 0.000%

    No Known Activations