© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135757
    Prev
    Next
    INDEX
    Explanations

    number of iterations or epochs

    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_37_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
    veni
    0.44
     copia
    0.37
    ovce
    0.37
     ob
    0.36
     hardy
    0.36
    Ꮤ
    0.36
     होतात
    0.36
    eni
    0.36
     ОБ
    0.36
    unter
    0.35
    POSITIVE LOGITS
    魔
    0.42
     articulating
    0.41
     diosa
    0.40
     sfai
    0.40
     docking
    0.38
     bombé
    0.38
     docks
    0.37
     hostel
    0.37
    िकांत
    0.36
    quinas
    0.35
    Activations Density 0.005%

    No Known Activations