© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196088
    Prev
    Next
    INDEX
    Explanations

    HTML closing tag pattern

    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_27_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
    ir
    0.40
     hosts
    0.40
     ఇ
    0.39
    asinya
    0.39
     ቫ
    0.38
    riy
    0.38
     sociologist
    0.38
    aret
    0.38
    arettes
    0.37
     redesign
    0.36
    POSITIVE LOGITS
    人員
    0.46
     لگے
    0.44
     مفت
    0.38
     إجراء
    0.37
    埸
    0.36
    اید
    0.35
     सुविधाजनक
    0.35
    RELAND
    0.35
    URCH
    0.35
     имел
    0.35
    Activations Density 0.000%

    No Known Activations