© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52690
    Prev
    Next
    INDEX
    Explanations

    year or date

    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
    ImageAlign
    0.35
    يقة
    0.34
    URANCE
    0.33
    കാര
    0.33
     setters
    0.33
    暠
    0.32
     UN
    0.32
     Secular
    0.32
    verte
    0.31
     اون
    0.31
    POSITIVE LOGITS
    qli
    0.36
    ܡ
    0.34
    ᄍ
    0.34
    joint
    0.33
    Qw
    0.32
    )=
    0.31
    <0xE3>
    0.31
    נע
    0.31
    affinity
    0.29
    ῴ
    0.29
    Activations Density 0.000%

    No Known Activations