© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200615
    Prev
    Next
    INDEX
    Explanations

    PTSD or pass

    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_6_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
     i
    1.09
     a
    0.87
    UM
    0.84
    UCH
    0.84
    ال
    0.80
    IR
    0.79
    "。
    0.79
     d
    0.77
     have
    0.77
     na
    0.75
    POSITIVE LOGITS
    t
    1.38
    v
    1.23
    ет
    1.12
    ди
    1.10
    n
    1.09
    y
    1.05
    es
    1.00
    vano
    0.98
    য়ের
    0.95
    d
    0.93
    Activations Density 0.000%

    No Known Activations