© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202405
    Prev
    Next
    INDEX
    Explanations

    clear out, cleared its

    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_12_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
     bridges
    0.65
    ла
    0.59
     tribulations
    0.56
     nodules
    0.55
     failures
    0.55
     consultancy
    0.54
     doping
    0.54
    夙
    0.54
     inefficiencies
    0.54
     deficiency
    0.53
    POSITIVE LOGITS
    t
    0.63
     Затем
    0.60
     »,
    0.58
    kt
    0.57
    R
    0.57
    endig
    0.56
     Во
    0.56
    ängt
    0.55
    ay
    0.55
     Ли
    0.55
    Activations Density 0.000%

    No Known Activations