© 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. 38778
    Prev
    Next
    INDEX
    Explanations

    completed/finished

    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
     come
    1.20
     Come
    1.10
    Come
    1.10
    come
    1.09
     COME
    0.96
    COME
    0.87
    来
    0.60
     comes
    0.58
    comes
    0.56
    來
    0.55
    POSITIVE LOGITS
    ropathy
    0.37
    arska
    0.36
     கரைச
    0.36
    र्वेद
    0.35
     heroism
    0.35
     सर्वा
    0.35
     보겠습니다
    0.35
    akyReLU
    0.34
    ctl
    0.33
    ibals
    0.33
    Activations Density 0.009%

    No Known Activations