© 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. 111959
    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
    a
    1.21
     at
    1.19
    5
    1.18
    ה
    1.16
    리
    1.16
    OH
    1.13
     about
    1.13
    EY
    1.09
     on
    1.05
    :
    1.05
    POSITIVE LOGITS
    ле
    1.13
    MinIntensity
    1.04
    tte
    1.02
    t
    1.00
    на
    1.00
    ט
    0.99
     Разби
    0.99
    SpriteCollision
    0.98
    tura
    0.96
     Интер
    0.96
    Activations Density 0.000%

    No Known Activations