© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157872
    Prev
    Next
    INDEX
    Explanations

    gu or gan sequence

    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_2_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
    ای
    1.18
     as
    1.16
    त
    1.16
    리
    1.08
     ocor
    1.03
    ת
    1.01
     discuter
    1.00
     fertil
    1.00
     bailar
    0.98
    .
    0.98
    POSITIVE LOGITS
    ang
    1.59
    in
    1.55
    é
    1.30
    ب
    1.18
    iners
    1.16
    ations
    1.13
    గ
    1.08
    inse
    1.04
    ir
    1.02
    inins
    0.99
    Activations Density 0.000%

    No Known Activations