© 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. 221192
    Prev
    Next
    INDEX
    Explanations

    VirtualBox

    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
     abide
    0.66
     plais
    0.64
    <0x98>
    0.62
     despise
    0.62
     PWMB
    0.61
    ח
    0.61
     }}
    0.60
     rôle
    0.59
     surmounted
    0.59
     prisma
    0.58
    POSITIVE LOGITS
    com
    0.69
     a
    0.66
    ip
    0.65
    ov
    0.63
    be
    0.63
    ft
    0.63
    ha
    0.63
    larg
    0.63
     آنے
    0.63
    ag
    0.62
    Activations Density 0.000%

    No Known Activations