© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39951
    Prev
    Next
    INDEX
    Explanations

    oh no

    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_11_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
    b
    0.82
    ب
    0.82
    w
    0.73
    ag
    0.73
    ह
    0.71
    g
    0.71
    Z
    0.70
    r
    0.69
    غ
    0.68
    ET
    0.67
    POSITIVE LOGITS
    urally
    0.62
     retaliation
    0.60
     réfé
    0.60
     :]
    0.60
     वार्ता
    0.59
     apologise
    0.58
     polarisation
    0.55
    ﻢ
    0.55
     collage
    0.55
     OBE
    0.55
    Activations Density 0.001%

    No Known Activations