© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78281
    Prev
    Next
    INDEX
    Explanations

    list items

    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_53_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
    并且
    0.41
    म्बर
    0.40
     앞으로
    0.39
    並且
    0.38
     %>',
    0.38
     ইত্যাদি
    0.36
    廰
    0.35
    కు
    0.35
    是在
    0.35
    сё
    0.33
    POSITIVE LOGITS
    duh
    0.34
    obviously
    0.34
    phenoxymethyl
    0.32
    rhein
    0.32
     ebenso
    0.32
    itôt
    0.32
     Unterschied
    0.31
     clerg
    0.31
    illiant
    0.31
     oWord
    0.31
    Activations Density 0.045%

    No Known Activations