© 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. 111885
    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
    ani
    1.18
    R
    1.00
    IN
    0.91
    ino
    0.91
    ANG
    0.89
    EP
    0.89
    ali
    0.89
    EL
    0.88
    ARG
    0.86
    Alchemy
    0.86
    POSITIVE LOGITS
    i
    2.14
    ي
    2.00
    m
    1.30
    يته
    1.26
    u
    1.24
    י
    1.23
    d
    1.22
    t
    1.20
    ről
    1.16
    د
    1.15
    Activations Density 0.000%

    No Known Activations