© 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. 82235
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     legít
    0.43
    lege
    0.40
    <unused23>
    0.38
    idget
    0.37
     Operate
    0.37
     rp
    0.37
    lessness
    0.36
     lepton
    0.36
    rp
    0.35
     centuries
    0.35
    POSITIVE LOGITS
     চ্যালেঞ্জ
    0.41
     CY
    0.37
     限
    0.37
    NAB
    0.37
     Bay
    0.37
     డా
    0.36
    setCurrent
    0.36
    ILabel
    0.35
     vur
    0.35
    ‌కు
    0.35
    Activations Density 0.001%

    No Known Activations