© 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. 235702
    Prev
    Next
    INDEX
    Explanations

    free pdfs

    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
    lingu
    0.41
     म्ह
    0.41
    اسی
    0.40
    FCO
    0.39
    䒠
    0.38
    Obl
    0.37
    MainBinding
    0.36
     Obl
    0.36
    üml
    0.36
    ceded
    0.36
    POSITIVE LOGITS
    ᒎ
    0.43
    bots
    0.41
     Samantha
    0.41
     Grave
    0.40
     Gravel
    0.39
     Sammy
    0.38
    iklet
    0.38
    Samantha
    0.38
     глу
    0.38
    itel
    0.37
    Activations Density 0.000%

    No Known Activations