© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45512
    Prev
    Next
    INDEX
    Explanations

    guess calculation, top trim, shooting, crossing river

    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_3_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
    ет
    0.71
    не
    0.68
    .
    0.68
     thấy
    0.66
     assassination
    0.64
     семейства
    0.64
     nightmares
    0.64
     cramps
    0.64
    a
    0.63
     с
    0.63
    POSITIVE LOGITS
    트
    0.77
    다
    0.66
    hava
    0.63
    ة
    0.63
    ib
    0.62
    ลำ
    0.61
    ing
    0.60
    的名字
    0.59
    儘
    0.59
    야
    0.58
    Activations Density 0.000%

    No Known Activations