© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    Sakaguchi, Sakura, Alexandra Paul

    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_38_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
    ទំន
    0.41
    朢
    0.40
    തന്ത്ര
    0.39
    شاد
    0.38
     انسان
    0.36
    وث
    0.36
    üge
    0.36
     undue
    0.35
     cigar
    0.35
    众
    0.34
    POSITIVE LOGITS
    Pet
    0.42
     pee
    0.41
    Тре
    0.39
     PET
    0.38
     Pet
    0.38
    hips
    0.37
     τ
    0.36
     пос
    0.36
     petals
    0.36
     OWN
    0.36
    Activations Density 0.020%

    No Known Activations