© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215358
    Prev
    Next
    INDEX
    Explanations

    short turnaround. | gone mad

    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_16_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
    0.59
    spirit
    0.53
    a
    0.49
    types
    0.48
    to
    0.47
    ना
    0.46
    Spirit
    0.46
     empty
    0.45
    ะไร
    0.44
    一
    0.44
    POSITIVE LOGITS
     equates
    0.47
     thinks
    0.44
     şə
    0.43
     Diario
    0.43
    اموش
    0.43
    ptious
    0.42
    ︶
    0.42
     지도
    0.41
     candid
    0.41
    GHz
    0.41
    Activations Density 0.000%

    No Known Activations