© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193907
    Prev
    Next
    INDEX
    Explanations

    sequence ABCDEF

    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_4_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
    ق
    1.27
    י
    1.19
    9
    1.18
    ле
    1.16
    си
    1.10
    4
    1.08
    ،
    1.05
    f
    1.04
    5
    1.04
    。
    1.04
    POSITIVE LOGITS
    ul
    1.14
    um
    1.01
    ing
    0.96
     in
    0.91
     frü
    0.86
     sikk
    0.82
    nál
    0.81
    oš
    0.79
     foci
    0.79
     Nautilus
    0.78
    Activations Density 0.003%

    No Known Activations