© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163692
    Prev
    Next
    INDEX
    Explanations

    medical problems, database columns, code definitions

    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_13_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
    }$
    0.51
     retiring
    0.47
     presidenta
    0.47
    iterator
    0.44
     necesaria
    0.43
    ატ
    0.43
    }$,
    0.42
     जाएगी
    0.42
    attro
    0.42
     trece
    0.42
    POSITIVE LOGITS
     Ariel
    0.55
    Вот
    0.54
     Sirius
    0.54
    İlk
    0.52
    Bers
    0.51
     Bers
    0.50
    İM
    0.50
    Height
    0.50
    Մ
    0.50
    Се
    0.49
    Activations Density 0.000%

    No Known Activations