© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31031
    Prev
    Next
    INDEX
    Explanations

    fine-tuning

    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_7_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
     or
    0.50
    на
    0.48
    ک
    0.46
    ید
    0.45
     and
    0.45
    S
    0.43
    л
    0.43
    に
    0.43
    w
    0.42
    ב
    0.41
    POSITIVE LOGITS
    you
    0.47
    {
    0.34
    (
    0.33
    als
    0.33
    matic
    0.32
    iate
    0.32
    你也
    0.32
     I
    0.31
    ében
    0.31
    ä
    0.31
    Activations Density 0.006%

    No Known Activations