© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60394
    Prev
    Next
    INDEX
    Explanations

    toward

    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_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
     for
    1.30
     not
    1.20
     from
    1.14
     l
    1.11
     n
    1.07
    ާމ
    1.05
     L
    1.03
    />
    1.02
     shy
    1.02
     t
    1.01
    POSITIVE LOGITS
    the
    1.73
    न
    1.39
    к
    1.38
    น
    1.34
    ки
    1.34
    я
    1.30
    ن
    1.27
    ش
    1.23
    на
    1.23
    of
    1.20
    Activations Density 0.000%

    No Known Activations