© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17739
    Prev
    Next
    INDEX
    Explanations

    experiencing unwanted sexual thoughts or urges

    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_34_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
     slices
    0.43
    ையா
    0.39
     prefixed
    0.38
    istoire
    0.38
    भव
    0.38
    kovskij
    0.38
    }`).
    0.37
     wafers
    0.37
    communic
    0.36
     ()=>
    0.36
    POSITIVE LOGITS
     этого
    0.43
     unsatisfied
    0.41
    があり
    0.39
     لهذا
    0.38
     цього
    0.37
    があって
    0.37
     deste
    0.36
    વાના
    0.36
    ającego
    0.36
    EDGE
    0.36
    Activations Density 0.032%

    No Known Activations