© 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. 235507
    Prev
    Next
    INDEX
    Explanations

    thing

    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
    かず
    0.40
    Lim
    0.39
    舒服
    0.39
    𝓎
    0.38
     chay
    0.36
    衫
    0.36
    ToBase
    0.36
     jamais
    0.35
     ஒன்ற
    0.35
     things
    0.35
    POSITIVE LOGITS
    ථ
    0.41
    ponible
    0.39
    ^{'
    0.38
    خاص
    0.38
    thr
    0.38
     ब्ले
    0.36
    Need
    0.36
    becomes
    0.36
     শু
    0.35
     বেল
    0.34
    Activations Density 0.002%

    No Known Activations