© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135010
    Prev
    Next
    INDEX
    Explanations

    al- followed by hyphen

    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
    t
    1.44
    h
    1.04
    c
    1.02
    al
    1.01
    e
    0.96
    at
    0.95
    i
    0.90
    ce
    0.89
    lul
    0.89
     prefque
    0.88
    POSITIVE LOGITS
    K
    1.35
    B
    1.34
    F
    1.29
    J
    1.16
    O
    1.12
    U
    1.09
    ER
    1.01
    S
    0.99
    D
    0.99
    E
    0.98
    Activations Density 0.000%

    No Known Activations