© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39086
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Closing
    0.44
     closing
    0.44
    Архі
    0.43
     Closing
    0.41
    いただきました
    0.38
    ᵕ
    0.38
     beg
    0.37
     finais
    0.36
     colocado
    0.36
    られました
    0.35
    POSITIVE LOGITS
    ESE
    0.38
    izan
    0.38
     fondant
    0.38
    aye
    0.38
    ++]
    0.37
    稃
    0.37
    mgr
    0.37
    ahme
    0.37
     Es
    0.37
    innah
    0.37
    Activations Density 0.001%

    No Known Activations