© 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. 68502
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    ML
    0.43
    ഹു
    0.40
    NDE
    0.40
    形の
    0.38
    СС
    0.38
    形
    0.37
     μορ
    0.37
    ళ్ళ
    0.36
    ml
    0.36
    icule
    0.36
    POSITIVE LOGITS
     Leach
    0.39
     레
    0.38
    льность
    0.38
    ষা
    0.38
     mathsize
    0.37
    渗透
    0.37
    労
    0.35
    Ծ
    0.35
    ванне
    0.35
     Siamo
    0.34
    Activations Density 0.001%

    No Known Activations