© 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. 126168
    Prev
    Next
    INDEX
    Explanations

    ense suffixes

    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
    諾
    0.73
     liebe
    0.64
    ]="
    0.63
    ），
    0.62
    }
    0.62
     wereld
    0.60
     ചോദ്യ
    0.60
    我
    0.59
    $",
    0.58
    Schwarz
    0.58
    POSITIVE LOGITS
    ,
    1.01
    िंग
    0.84
    :
    0.82
     expedited
    0.82
    t
    0.81
    та
    0.80
    ной
    0.80
    र
    0.77
    د
    0.76
    pe
    0.75
    Activations Density 0.001%

    No Known Activations