© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112899
    Prev
    Next
    INDEX
    Explanations

    screaming or screeching

    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
    t
    0.96
     در
    0.93
     informó
    0.89
     إ
    0.88
     in
    0.82
     في
    0.82
     މ
    0.81
    in
    0.80
     సు
    0.80
     flares
    0.80
    POSITIVE LOGITS
    า
    1.25
    ة
    1.17
    ี
    1.00
    सी
    0.99
    ુ
    0.95
    ный
    0.92
    ם
    0.89
    ार
    0.88
    ला
    0.87
    ס
    0.87
    Activations Density 0.001%

    No Known Activations