© 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. 170634
    Prev
    Next
    INDEX
    Explanations

    nb / nab

    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
     Sweet
    0.44
     sweet
    0.44
    Sweet
    0.43
    sweet
    0.42
    甜
    0.42
     ngọt
    0.39
     sweetheart
    0.39
     sweetness
    0.38
    矾
    0.38
     слад
    0.37
    POSITIVE LOGITS
     nb
    2.95
     نب
    2.92
    NB
    2.89
     NB
    2.89
    nb
    2.81
     nab
    2.73
     Nb
    2.69
    Nb
    2.67
     Nab
    2.67
    Nab
    2.61
    Activations Density 0.024%

    No Known Activations