© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57177
    Prev
    Next
    INDEX
    Explanations

    sloshing

    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_11_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
    齦
    0.55
    gı
    0.54
    ueva
    0.52
    ferences
    0.52
    modo
    0.51
     چنانچہ
    0.51
    council
    0.51
    𒈾
    0.51
    ပိုင်း
    0.50
    𝘥
    0.50
    POSITIVE LOGITS
    ളി
    0.56
     minimize
    0.51
    는
    0.48
     pr
    0.48
     succeed
    0.47
     je
    0.47
    ార్క్
    0.46
     denote
    0.46
    I
    0.46
     הע
    0.46
    Activations Density 0.000%

    No Known Activations