© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157789
    Prev
    Next
    INDEX
    Explanations

    gpt

    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_2_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
    л
    1.53
    ל
    1.49
    ன்
    1.48
    ר
    1.42
    ル
    1.36
    ش
    1.35
    is
    1.34
    ل
    1.27
    リ
    1.27
    نا
    1.20
    POSITIVE LOGITS
    ut
    1.71
    ab
    1.36
    RO
    1.18
    ul
    1.16
    iz
    1.13
    gebiet
    1.13
    az
    1.12
    ew
    1.10
    over
    1.07
    、“
    1.07
    Activations Density 0.002%

    No Known Activations