© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149246
    Prev
    Next
    INDEX
    Explanations

    css file links

    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_23_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
    多
    0.42
    ")
    0.41
    ゲ
    0.40
     seizures
    0.40
    DR
    0.39
    mera
    0.38
     questionnaires
    0.38
    mr
    0.37
    Custom
    0.37
    oss
    0.37
    POSITIVE LOGITS
    괵
    0.44
    positroid
    0.44
     букмекерлик
    0.44
    ப்பான்
    0.44
     chinois
    0.42
    ίων
    0.42
    нять
    0.42
    చిన
    0.41
     Гуляць
    0.41
    uvieron
    0.41
    Activations Density 0.000%

    No Known Activations