© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123024
    Prev
    Next
    INDEX
    Explanations

    IMDb links

    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
     Throw
    0.43
     PAYMENT
    0.42
    Throw
    0.42
     Pine
    0.41
     Toss
    0.41
     caza
    0.40
     Zahlung
    0.40
     목
    0.39
     threw
    0.39
    Pago
    0.39
    POSITIVE LOGITS
    𝟖
    0.42
    ട്ടം
    0.41
     formate
    0.39
    listdir
    0.38
     breakpoints
    0.36
    oxane
    0.36
     configuring
    0.35
    ല്ലാതെ
    0.35
    ODI
    0.35
     defender
    0.35
    Activations Density 0.000%

    No Known Activations