© 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. 45010
    Prev
    Next
    INDEX
    Explanations

    for a reason

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Detailed
    0.47
     Generated
    0.47
     Articles
    0.45
     Absence
    0.45
    aculate
    0.44
    🇴
    0.43
    脤
    0.42
    𝕠
    0.41
     Fixed
    0.41
     absences
    0.41
    POSITIVE LOGITS
    lös
    0.42
    v
    0.39
     kali
    0.39
    hesh
    0.38
     gim
    0.38
    kali
    0.38
     vezes
    0.37
    leep
    0.37
     다시
    0.37
    ci
    0.36
    Activations Density 0.001%

    No Known Activations