© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34795
    Prev
    Next
    INDEX
    Explanations

    morons, Morroco, Mormons, Morrison, Morrisons

    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_3_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
    s
    1.18
    ING
    0.98
     I
    0.93
     r
    0.89
    ی
    0.89
     with
    0.86
     about
    0.86
    ;
    0.85
     up
    0.85
     e
    0.84
    POSITIVE LOGITS
    hwa
    0.83
    hdu
    0.80
    các
    0.75
    𝒑
    0.74
    huh
    0.73
    fastq
    0.73
    parquet
    0.73
    нда
    0.73
    pawns
    0.73
    padă
    0.72
    Activations Density 0.000%

    No Known Activations