© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52730
    Prev
    Next
    INDEX
    Explanations

    :**

    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_55_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
    𝘐
    0.42
    Ἰ
    0.39
    Liter
    0.38
    Growing
    0.38
    Likes
    0.38
    akey
    0.37
    urger
    0.37
    ln
    0.36
    Hint
    0.36
    Cookie
    0.36
    POSITIVE LOGITS
     upon
    0.39
     figure
    0.38
     целом
    0.37
     سته
    0.36
     }}(\
    0.36
     rationality
    0.36
    宄
    0.36
     fidelity
    0.35
    ηση
    0.35
     institutes
    0.35
    Activations Density 0.000%

    No Known Activations