© 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. 206246
    Prev
    Next
    INDEX
    Explanations

    technical tasks

    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
    following
    0.54
    !}
    0.50
    Following
    0.50
     following
    0.49
     Following
    0.44
    regulating
    0.43
    applied
    0.43
     FOLLOWING
    0.43
    Applied
    0.43
    significant
    0.42
    POSITIVE LOGITS
    ..");
    0.49
     spécialement
    0.49
     specially
    0.47
    ..”
    0.47
    ..
    0.46
     खासतौर
    0.44
    .."
    0.43
     специально
    0.43
     Regardless
    0.43
     đặc
    0.43
    Activations Density 0.000%

    No Known Activations