© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172088
    Prev
    Next
    INDEX
    Explanations

    just letting you know that I

    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_20_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
    ه
    0.51
    روع
    0.47
    اگر
    0.47
    ଷ
    0.46
     muziek
    0.44
    כ
    0.44
    مع
    0.43
    ח
    0.42
     الرح
    0.42
    OBJECT
    0.42
    POSITIVE LOGITS
     Pasar
    0.53
     regulation
    0.52
     regulated
    0.50
     regulación
    0.50
     regulating
    0.49
    regulated
    0.47
     talented
    0.46
     regulate
    0.46
     sporadic
    0.46
     porosity
    0.46
    Activations Density 0.002%

    No Known Activations