© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150518
    Prev
    Next
    INDEX
    Explanations

    code and commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    凑
    0.37
        
    0.35
    റായി
    0.35
    kA
    0.34
    ruik
    0.33
     criou
    0.33
    ydent
    0.33
    ulfill
    0.33
    ukkig
    0.32
    Ҷ
    0.32
    POSITIVE LOGITS
     \
    2.17
    \
    1.42
     -\
    1.29
    ~\
    1.28
    -\
    1.26
     ~\
    1.19
    =\
    1.13
    ,\
    1.11
    ;\
    1.08
     \'
    1.07
    Activations Density 0.001%

    No Known Activations