© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205971
    Prev
    Next
    INDEX
    Explanations

    Cincinnati

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Cle
    0.51
    Cle
    0.46
    কুম
    0.45
     cle
    0.44
    清
    0.42
    им
    0.41
     Eighth
    0.41
     CLE
    0.40
    kle
    0.40
    まれた
    0.38
    POSITIVE LOGITS
     redress
    0.38
    agerie
    0.37
     contain
    0.37
    Monster
    0.35
     graders
    0.35
    อกาส
    0.35
    ㄶ
    0.35
    ULTY
    0.35
    picture
    0.35
     gps
    0.35
    Activations Density 0.000%

    No Known Activations