© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85677
    Prev
    Next
    INDEX
    Explanations

    can make people

    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_23_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
    lust
    0.10
    list
    0.10
    >.
    0.10
    गमन
    0.10
     lust
    0.09
    bl
    0.09
    with
    0.09
    log
    0.09
    ŧ
    0.09
    laşt
    0.09
    POSITIVE LOGITS
     OSI
    0.09
     kammam
    0.08
    ヘ
    0.08
     másik
    0.08
     verschillende
    0.08
    亥
    0.08
     Allocated
    0.08
     RAND
    0.08
     RBIs
    0.08
     outfile
    0.08
    Activations Density 0.037%

    No Known Activations