© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108772
    Prev
    Next
    INDEX
    Explanations

    goblin boys, guide

    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_1_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
    ל
    1.63
    л
    1.34
     avrà
    1.22
     następnie
    1.20
     debía
    1.17
     pusieron
    1.17
     llevaba
    1.16
     miał
    1.16
    ও
    1.16
     tendría
    1.15
    POSITIVE LOGITS
    ir
    1.48
    m
    1.44
    ell
    1.40
    :
    1.38
    y
    1.34
    ak
    1.33
    ed
    1.30
    ok
    1.29
    ere
    1.28
    ly
    1.27
    Activations Density 0.000%

    No Known Activations