© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17752
    Prev
    Next
    INDEX
    Explanations

    purposes only

    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
     '.
    0.42
    weaving
    0.41
     weaving
    0.39
    érance
    0.38
     लीजिए
    0.38
     dä
    0.38
     weave
    0.37
    <0xB3>
    0.37
     plunged
    0.37
    <0xDB>
    0.36
    POSITIVE LOGITS
    ستخدم
    0.42
    capacitor
    0.36
    менту
    0.36
     flipping
    0.35
     Montpellier
    0.35
    EFI
    0.35
     कैपिट
    0.35
     Fli
    0.35
    昛
    0.33
     Canadi
    0.33
    Activations Density 0.002%

    No Known Activations