© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257806
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
    те
    0.48
    وت
    0.46
    Ч
    0.45
     затем
    0.44
    Α
    0.44
    Ｔ
    0.44
     സ്ത്രീ
    0.43
     somatic
    0.42
    الث
    0.42
     সেটাই
    0.42
    POSITIVE LOGITS
    Minn
    0.39
    ]?.
    0.39
    Guid
    0.37
     ignoreString
    0.37
    <unused60>
    0.37
     ?>"
    0.37
    Caf
    0.37
     nondestructive
    0.37
    Honey
    0.36
     craindre
    0.36
    Activations Density 0.000%

    No Known Activations