© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210097
    Prev
    Next
    INDEX
    Explanations

    spiral, opposite, node arrangements

    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_20_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
    ieß
    0.46
    amiliar
    0.45
     informativo
    0.45
     músculos
    0.43
     எழு
    0.42
    鎧
    0.42
     smashing
    0.42
    ddagger
    0.41
     pozycji
    0.41
    ഛ
    0.41
    POSITIVE LOGITS
    usually
    0.51
     usually
    0.50
    Usually
    0.46
    في
    0.45
     Usually
    0.45
    ”(
    0.44
                         
    0.44
    通常
    0.44
    owna
    0.43
     ubuntu
    0.41
    Activations Density 0.000%

    No Known Activations