© 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. 57036
    Prev
    Next
    INDEX
    Explanations

    prepare for

    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
    t
    0.71
    もしくは
    0.62
    είται
    0.59
    ید
    0.59
    の値
    0.59
    (
    0.57
    ן
    0.57
    หรือ
    0.57
    نید
    0.55
     américains
    0.55
    POSITIVE LOGITS
    })(\
    0.59
    }";
    0.56
     পড়াশ
    0.52
    }")
    0.52
    }/\
    0.52
    TEX
    0.52
    }</
    0.51
     కూ
    0.50
    gard
    0.50
     Ма
    0.50
    Activations Density 0.002%

    No Known Activations