© 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. 61193
    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
    يد
    1.55
    ని
    1.20
    3
    1.13
    ין
    1.12
    𝙚
    1.12
    يل
    1.09
     مي‌
    1.05
    ள்ளனர்
    1.04
    দের
    1.02
    >′
    1.02
    POSITIVE LOGITS
    R
    1.53
    V
    1.51
    D
    1.41
    K
    1.34
    was
    1.30
    S
    1.28
    I
    1.27
     was
    1.23
    G
    1.23
    h
    1.21
    Activations Density 0.000%

    No Known Activations