© 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. 33926
    Prev
    Next
    INDEX
    Explanations

    terms with, then

    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
    ب
    0.82
    )
    0.71
    }).
    0.67
     Arabs
    0.61
    ด
    0.61
    }",
    0.59
     Britann
    0.59
     বলেছে
    0.59
     Judas
    0.59
     Arab
    0.59
    POSITIVE LOGITS
    t
    1.02
    y
    0.82
    em
    0.72
    od
    0.71
    lily
    0.62
    aient
    0.61
    ej
    0.60
    hana
    0.59
    oč
    0.59
    vamos
    0.57
    Activations Density 0.005%

    No Known Activations