© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33750
    Prev
    Next
    INDEX
    Explanations

    then introducing a new point

    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_31_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
    َال
    0.46
    the
    0.42
     शिवाय
    0.42
     the
    0.40
    那个
    0.38
    みます
    0.38
    ...">
    0.37
     sheer
    0.37
    那
    0.37
     kisah
    0.36
    POSITIVE LOGITS
     صورت
    0.42
    !।
    0.42
    력을
    0.39
     TS
    0.38
     NS
    0.38
    PSA
    0.37
    [*
    0.37
     jednom
    0.37
     DPS
    0.37
    തേ
    0.36
    Activations Density 0.000%

    No Known Activations