© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37441
    Prev
    Next
    INDEX
    Explanations

    Brand name endings like -us, -ula, -uba

    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
    ing
    1.05
     I
    0.79
    ும்
    0.69
     It
    0.66
    tim
    0.65
    arse
    0.62
     hv
    0.61
    ING
    0.60
    itul
    0.59
     halv
    0.59
    POSITIVE LOGITS
    ل
    1.13
    л
    0.95
    いる
    0.89
    رک
    0.88
    や
    0.88
    رین
    0.87
    ר
    0.86
    로
    0.83
    на
    0.82
    나
    0.82
    Activations Density 0.018%

    No Known Activations