© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32747
    Prev
    Next
    INDEX
    Explanations

    married couple

    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_31_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
     博
    0.35
     लीक
    0.33
     Lava
    0.32
    weeney
    0.32
     erlä
    0.30
     Recon
    0.30
    ုံး
    0.29
     måtte
    0.29
    े
    0.29
     предстоя
    0.29
    POSITIVE LOGITS
     نہيں
    0.34
     poes
    0.32
     scepticism
    0.32
     اخ
    0.31
     குழ
    0.31
    ানুভূতি
    0.31
     preparación
    0.31
    improved
    0.31
     complejidad
    0.30
     denials
    0.30
    Activations Density 0.000%

    No Known Activations