© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143168
    Prev
    Next
    INDEX
    Explanations

    impeller, speedometer, undervaluation

    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_0_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
    很
    1.32
    سی
    1.30
     an
    1.23
    는데
    1.21
     opposites
    1.20
     voisins
    1.13
    ce
    1.12
    اری
    1.10
     repris
    1.10
    ール
    1.09
    POSITIVE LOGITS
    us
    1.63
    ि
    1.48
    ता
    1.43
    !
    1.38
    ie
    1.37
    r
    1.34
    ?
    1.31
    um
    1.27
    ал
    1.27
    ो
    1.27
    Activations Density 0.000%

    No Known Activations