© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64444
    Prev
    Next
    INDEX
    Explanations

    didn't

    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_41_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
     isn
    0.39
    insi
    0.38
    INS
    0.38
     won
    0.37
     doesn
    0.37
    یس
    0.37
     甘
    0.36
    甘
    0.36
    Webster
    0.35
    INDUST
    0.35
    POSITIVE LOGITS
     Didn
    1.59
     didn
    1.53
    Didn
    1.48
    didn
    1.40
     didnt
    1.38
    Did
    1.31
     Did
    1.27
    did
    1.22
    DID
    1.14
     did
    1.12
    Activations Density 0.337%

    No Known Activations