© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30933
    Prev
    Next
    INDEX
    Explanations

    Answer Choices:

    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_40_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
    ร็จ
    0.42
    Cheese
    0.41
     Cheese
    0.40
    螫
    0.40
     nChar
    0.39
    LIED
    0.38
     krishna
    0.38
     হীরু
    0.38
    imeric
    0.38
    菂
    0.38
    POSITIVE LOGITS
     vigilant
    0.36
    SOLD
    0.36
     ret
    0.35
     Retire
    0.35
     rat
    0.35
    িকা
    0.35
     Barlow
    0.35
     herpes
    0.34
     ilustraciones
    0.34
     collapse
    0.34
    Activations Density 0.000%

    No Known Activations