© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22980
    Prev
    Next
    INDEX
    Explanations

    entity relations

    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_56_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
     *$
    0.38
     *\
    0.37
     PPM
    0.36
     gene
    0.36
    )<<
    0.36
    veratrol
    0.35
     cole
    0.35
    _{(\
    0.35
     $<$
    0.34
     filter
    0.34
    POSITIVE LOGITS
     есть
    0.71
    есть
    0.54
     Есть
    0.52
    Есть
    0.51
     equip
    0.47
    있는
    0.46
     equips
    0.46
    있
    0.45
    Prob
    0.44
     있으
    0.42
    Activations Density 0.000%

    No Known Activations