© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194916
    Prev
    Next
    INDEX
    Explanations

    #include statements

    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_27_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
     наблюда
    0.42
    珼
    0.41
     পরীক্ষা
    0.41
     тай
    0.38
    amide
    0.38
    <unused335>
    0.38
    াবলীর
    0.38
    ✖
    0.38
    মালা
    0.37
    rometer
    0.37
    POSITIVE LOGITS
     excluding
    0.39
     śred
    0.39
     NoContent
    0.38
     barring
    0.37
     chor
    0.35
     relativement
    0.35
     constitut
    0.35
    箕
    0.35
    饶
    0.35
     bare
    0.35
    Activations Density 0.000%

    No Known Activations