© 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. 261971
    Prev
    Next
    INDEX
    Explanations

    cycles per second/minute

    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
     ആരാ
    0.44
     unauthorized
    0.43
    μι
    0.42
    ോഷ്യ
    0.42
     ఘ
    0.42
     unauthorised
    0.41
     কিছু
    0.40
    Security
    0.40
     microwave
    0.40
     لان
    0.39
    POSITIVE LOGITS
     UVA
    0.41
    }((
    0.37
    uğ
    0.36
    刊行
    0.36
     persuas
    0.36
    omod
    0.36
    更多
    0.35
    更多的
    0.35
    ऑन
    0.35
    ocs
    0.35
    Activations Density 0.003%

    No Known Activations