© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127927
    Prev
    Next
    INDEX
    Explanations

    Bosch, BSN, nova, Fest

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    )
    1.09
    ]
    0.91
    }
    0.88
    )&=
    0.86
    )…
    0.78
     excerpts
    0.75
    )=
    0.75
    ἦ
    0.75
    ).”
    0.73
    )”.
    0.73
    POSITIVE LOGITS
    ل
    0.80
    ED
    0.77
    ing
    0.77
    一
    0.73
    ins
    0.70
    ia
    0.69
    ron
    0.68
    ü
    0.68
     получится
    0.68
    ris
    0.67
    Activations Density 0.000%

    No Known Activations