© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39087
    Prev
    Next
    INDEX
    Explanations

    listing 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_57_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
    それ
    0.39
    えます
    0.39
     czy
    0.38
    …).
    0.38
    …)
    0.37
    …</
    0.37
     CCc
    0.37
     সহ
    0.35
     strCmd
    0.35
    >>)
    0.35
    POSITIVE LOGITS
     ون
    1.37
     וכ
    1.00
     따
    0.94
     기타
    0.74
    その他
    0.73
     ta
    0.66
    その他の
    0.62
    따
    0.57
     Ta
    0.56
    Ta
    0.55
    Activations Density 0.004%

    No Known Activations