© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14121
    Prev
    Next
    INDEX
    Explanations

    indentation spaces

    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_40_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
     Syrup
    0.42
    桷
    0.40
     lahan
    0.40
     presented
    0.38
    Spacing
    0.37
     Bernal
    0.36
     Absor
    0.36
    Presented
    0.35
     Styled
    0.35
     Bestell
    0.35
    POSITIVE LOGITS
     indications
    0.44
     indicators
    0.39
     indicates
    0.39
    >()
    0.38
     meg
    0.37
     deeper
    0.36
     indication
    0.36
    indications
    0.36
     indicar
    0.35
     पोस्टमार्टम
    0.35
    Activations Density 0.008%

    No Known Activations