© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133398
    Prev
    Next
    INDEX
    Explanations

    resonate with

    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_6_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
    6
    1.11
    1
    1.05
    ف
    1.00
    يد
    0.96
    СС
    0.93
    تر
    0.93
    к
    0.92
    ्व
    0.90
    мес
    0.90
    ।
    0.89
    POSITIVE LOGITS
    d
    1.40
     configur
    1.04
    ش
    1.04
     circul
    0.98
    ;
    0.98
     opos
    0.97
     modul
    0.96
     program
    0.96
     journaling
    0.96
     promis
    0.95
    Activations Density 0.001%

    No Known Activations