© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81064
    Prev
    Next
    INDEX
    Explanations

    notation marks

    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
    ሠራ
    0.41
    âm
    0.39
    тріш
    0.39
    ální
    0.38
    iam
    0.38
     consequat
    0.37
    𝔹
    0.37
    quat
    0.37
    ẩ
    0.37
    ṁ
    0.37
    POSITIVE LOGITS
    সই
    0.38
     nevo
    0.37
    ım
    0.36
     stork
    0.35
     dipl
    0.34
     gasp
    0.34
     figure
    0.33
     tecn
    0.33
     silently
    0.32
     taala
    0.32
    Activations Density 0.000%

    No Known Activations