© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122665
    Prev
    Next
    INDEX
    Explanations

    Evelyn with a last name

    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_37_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
    ويم
    0.40
     ክ
    0.40
    ))^
    0.38
    ಡ್ಡ
    0.37
    ))-
    0.37
    鈷
    0.37
     Dimensional
    0.36
     Ад
    0.35
    III
    0.35
     सुंदरता
    0.34
    POSITIVE LOGITS
     lie
    0.38
     Titles
    0.37
    ሁ
    0.36
     benötigen
    0.36
    garakan
    0.36
    olska
    0.35
     Arach
    0.35
     requieren
    0.35
     Ins
    0.35
     multiple
    0.34
    Activations Density 0.000%

    No Known Activations