© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219951
    Prev
    Next
    INDEX
    Explanations

    throwing something

    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
    𝐬
    0.40
    सों
    0.38
     ☑
    0.37
    stech
    0.37
    unjung
    0.36
     வாக
    0.36
     напол
    0.35
    芴
    0.35
    斻
    0.35
     Jann
    0.35
    POSITIVE LOGITS
    rq
    0.36
     身
    0.36
     trại
    0.35
     প্রভ
    0.34
    кли
    0.34
     उत्ते
    0.34
     Farms
    0.34
    ración
    0.33
    クリック
    0.33
    OURCES
    0.33
    Activations Density 0.001%

    No Known Activations