© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198899
    Prev
    Next
    INDEX
    Explanations

    catch Exception

    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_27_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
     Seaton
    0.40
     சோ
    0.37
    व
    0.35
    Durham
    0.34
    Re
    0.34
    流れ
    0.34
    Rey
    0.33
    граммы
    0.33
     Rech
    0.33
    м
    0.33
    POSITIVE LOGITS
     खासदार
    0.43
    ibal
    0.42
     flats
    0.42
    ባቢ
    0.40
     Maler
    0.39
     misch
    0.39
     kaik
    0.39
     eligibility
    0.39
     integrating
    0.38
     Lulu
    0.38
    Activations Density 0.001%

    No Known Activations