© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40832
    Prev
    Next
    INDEX
    Explanations

    trauma and harm

    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
    es
    0.57
    os
    0.57
    em
    0.55
    ot
    0.50
     d
    0.48
    on
    0.48
    ag
    0.48
    an
    0.47
    am
    0.47
    ou
    0.47
    POSITIVE LOGITS
    Tipo
    0.49
     Secara
    0.47
     It
    0.47
    Tidak
    0.45
    Werk
    0.43
    It
    0.43
     Rohit
    0.43
    REFLECTION
    0.43
    পদ
    0.42
     Він
    0.42
    Activations Density 0.065%

    No Known Activations