© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198821
    Prev
    Next
    INDEX
    Explanations

    Spanish Inquisition

    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_15_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
     CMOS
    0.58
     Robot
    0.58
    क्स
    0.56
     Model
    0.56
     CELL
    0.56
     Lieb
    0.55
     LG
    0.55
     Ć
    0.55
    មី
    0.54
     costes
    0.54
    POSITIVE LOGITS
    rezent
    0.52
    educ
    0.49
    unter
    0.49
    fac
    0.49
    forc
    0.47
    ],'
    0.46
    sie
    0.46
    seven
    0.46
    演绎
    0.46
    ()]
    0.46
    Activations Density 0.000%

    No Known Activations