© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216687
    Prev
    Next
    INDEX
    Explanations

    harp

    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_50_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
     gradient
    0.41
     Gradient
    0.41
    nabla
    0.41
     बा
    0.38
     band
    0.37
     Bands
    0.37
    溝
    0.37
     ક
    0.36
     Regal
    0.36
     k
    0.36
    POSITIVE LOGITS
     har
    0.82
     h
    0.80
     ह
    0.71
    Har
    0.68
     ح
    0.66
     Har
    0.65
     harp
    0.65
    har
    0.64
     хар
    0.64
     hare
    0.63
    Activations Density 0.014%

    No Known Activations