© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163421
    Prev
    Next
    INDEX
    Explanations

    authors' academic actions

    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_31_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
     mouse
    0.37
    িলে
    0.37
     rig
    0.36
     কীটপত
    0.36
     dist
    0.36
    箱
    0.35
     widowed
    0.34
     சுற்றுச்சூழ
    0.34
     impover
    0.34
    🏭
    0.34
    POSITIVE LOGITS
    formed
    0.41
    acons
    0.39
     உதவி
    0.38
    Inter
    0.38
    alski
    0.38
    कौन
    0.36
    ზრ
    0.36
     службы
    0.35
     konsult
    0.35
     chữ
    0.35
    Activations Density 0.000%

    No Known Activations