© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253389
    Prev
    Next
    INDEX
    Explanations

    say '-'

    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
    –
    2.80
    .–
    1.89
    )–
    1.87
    ‒
    1.54
    −
    1.36
    ––
    1.35
     –,
    1.22
    €“
    1.20
    ndash
    1.05
    
    1.05
    POSITIVE LOGITS
     .\
    0.52
     ⚫
    0.51
    ⚫
    0.47
     ▼
    0.46
     ..
    0.45
     ~\
    0.44
    ㈣
    0.44
     ❤️
    0.42
    .$\
    0.39
    /</
    0.39
    Activations Density 0.029%

    No Known Activations