© 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. 20857
    Prev
    Next
    INDEX
    Explanations

    om

    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
    .[[
    0.40
    的方向
    0.39
    氤
    0.39
     laude
    0.37
     Did
    0.37
     tony
    0.37
    thood
    0.37
     Doris
    0.36
    }\|^{
    0.36
    اتھن
    0.36
    POSITIVE LOGITS
     tilbake
    0.44
     mijn
    0.42
    nog
    0.40
     nog
    0.40
    ّم
    0.38
     förs
    0.38
     daar
    0.38
     piek
    0.38
     pags
    0.37
     tillsammans
    0.37
    Activations Density 0.000%

    No Known Activations