© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207993
    Prev
    Next
    INDEX
    Explanations

    formatting

    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_56_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
    </blockquote>
    0.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
    NavBar
    0.37
    </footer>
    0.37
    эрэг
    0.36
     μέσα
    0.36
    <start_of_image>
    0.36
    municipal
    0.36
    🥅
    0.36
    penup
    0.35
    POSITIVE LOGITS
     PS
    0.43
    PS
    0.38
    𝐱
    0.36
     televis
    0.36
     Hild
    0.36
     increasingly
    0.35
    യില
    0.34
     FULL
    0.34
    찌
    0.34
    学び
    0.33
    Activations Density 0.005%

    No Known Activations