© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6239
    Prev
    Next
    INDEX
    Explanations

    AI safety refusals

    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_44_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
     tag
    0.48
    iral
    0.43
    tag
    0.41
     Tag
    0.40
     Ohm
    0.39
    ậu
    0.37
    Tag
    0.37
    偕
    0.37
     templateUrl
    0.37
     lom
    0.37
    POSITIVE LOGITS
    Charting
    0.41
     charismatic
    0.41
    arge
    0.40
    Coff
    0.40
    Lifecycle
    0.39
     അടുത്ത
    0.39
    liberal
    0.39
    Klas
    0.38
    प्लेस
    0.38
    Beef
    0.38
    Activations Density 0.011%

    No Known Activations