© 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. 85281
    Prev
    Next
    INDEX
    Explanations

    Nova, Bloom, Data, Group, Launcher

    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
    телем
    0.85
    ଞ
    0.71
    }$&
    0.68
    ان
    0.66
    وڑا
    0.66
     novembro
    0.64
    жмите
    0.64
    parsing
    0.63
    براير
    0.63
    )&=
    0.63
    POSITIVE LOGITS
    s
    0.91
     in
    0.89
    是
    0.86
     في
    0.77
    ă
    0.76
     könne
    0.76
    在
    0.75
     中
    0.75
     on
    0.74
     třeba
    0.74
    Activations Density 0.001%

    No Known Activations