© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160988
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ሶች
    0.50
    เซีย
    0.47
    త్మ
    0.47
    వంత
    0.46
    اد
    0.45
     Alloy
    0.45
    嘚
    0.45
    妛
    0.44
    స
    0.44
    似乎
    0.44
    POSITIVE LOGITS
    ερμαν
    0.62
     cominc
    0.60
    ă
    0.59
     margine
    0.58
     contatto
    0.57
     fatto
    0.56
     regole
    0.56
    നേ
    0.55
    يط
    0.54
     mancanza
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.