© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221760
    Prev
    Next
    INDEX
    Explanations

    edge detection, medical, policy, reconciliation

    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_10_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
    ي
    0.51
    c
    0.50
    ين
    0.47
     على
    0.47
    }):
    0.46
     maximized
    0.46
    على
    0.46
     عكس
    0.43
    ؛
    0.43
    }^{+}
    0.42
    POSITIVE LOGITS
    Շ
    0.47
     analges
    0.47
    Spot
    0.47
    ROE
    0.46
    ημ
    0.46
     verre
    0.45
    이제
    0.45
     पेंशन
    0.44
     사인
    0.44
     Γερμαν
    0.44
    Activations Density 0.000%

    No Known Activations