© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139766
    Prev
    Next
    INDEX
    Explanations

    VLSC

    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_12_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
    ン
    0.54
     bors
    0.52
     there
    0.50
     stripos
    0.49
     alkali
    0.48
     ende
    0.48
    >()
    0.48
     from
    0.47
     elettronica
    0.47
     easel
    0.47
    POSITIVE LOGITS
     மருத்துவ
    0.51
    Adopt
    0.51
     ROT
    0.50
    RP
    0.49
     செயல்
    0.48
     स्वास्थ्य
    0.47
     ሥራ
    0.47
     Reads
    0.47
     क
    0.47
     રોજ
    0.46
    Activations Density 0.000%

    No Known Activations