© 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. 205191
    Prev
    Next
    INDEX
    Explanations

    pick-up lines

    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
    1.12
    는
    0.89
    м
    0.86
    る
    0.86
    ৩
    0.84
    ર
    0.83
    וס
    0.81
    다
    0.80
    ר
    0.80
    де
    0.79
    POSITIVE LOGITS
    ill
    1.24
    and
    1.23
    ra
    1.16
    T
    1.14
    ter
    1.13
    E
    1.02
    ized
    1.01
    ab
    0.98
    all
    0.95
    K
    0.94
    Activations Density 0.000%

    No Known Activations