© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68426
    Prev
    Next
    INDEX
    Explanations

    ISA

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     Rtl
    0.40
    тельное
    0.39
    SCP
    0.39
    qk
    0.38
     Sér
    0.38
     sosten
    0.38
     CHP
    0.37
    )}}\
    0.37
    igueur
    0.37
     Séb
    0.37
    POSITIVE LOGITS
     ISA
    2.88
    ISA
    2.67
     isa
    2.56
    isa
    2.53
     Isa
    2.36
    Isa
    2.30
     ESA
    2.28
     ASA
    2.28
    ASA
    2.06
     asa
    2.05
    Activations Density 0.299%

    No Known Activations