© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58849
    Prev
    Next
    INDEX
    Explanations

    framing context

    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_11_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
     rằng
    0.71
    ेक
    0.62
    et
    0.61
     తగ్గి
    0.60
    쐐
    0.59
    يار
    0.59
     વ્યવ
    0.59
    ेंद्रीय
    0.57
    ipos
    0.57
    ታት
    0.57
    POSITIVE LOGITS
    )
    0.72
     attano
    0.58
     mediating
    0.56
    ),
    0.54
     acetate
    0.54
     BACKGROUND
    0.54
     such
    0.53
     I
    0.52
     abdomen
    0.52
     postpartum
    0.52
    Activations Density 0.007%

    No Known Activations