© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132197
    Prev
    Next
    INDEX
    Explanations

    checking if string starts with

    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_6_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
    -
    0.89
    ون
    0.81
    ING
    0.80
    ным
    0.70
    Butyl
    0.69
    ◌
    0.69
    вата
    0.68
    लम
    0.66
    ATE
    0.65
    ﻊ
    0.64
    POSITIVE LOGITS
    for
    1.01
    of
    0.98
    ak
    0.93
    ov
    0.93
    ock
    0.89
    and
    0.87
    io
    0.87
    on
    0.86
    an
    0.84
     autres
    0.81
    Activations Density 0.001%

    No Known Activations