© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204114
    Prev
    Next
    INDEX
    Explanations

    Fumio Kishida, Yoshishige Yoshida, Takaaki Kidani

    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_6_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
    p
    1.36
    v
    1.14
    é
    1.14
    h
    1.09
    id
    1.05
    x
    1.04
    c
    0.97
    k
    0.93
    al
    0.89
    st
    0.88
    POSITIVE LOGITS
     to
    1.12
     accords
    1.12
     on
    1.08
     arrays
    1.07
     markets
    1.02
     tracers
    1.02
     entities
    1.01
     attaques
    1.01
     artifacts
    0.99
     imports
    0.99
    Activations Density 0.000%

    No Known Activations