© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    Stalin or Ivan

    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_13_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
     rinsed
    0.53
     cleansed
    0.52
     invalidated
    0.47
     uncl
    0.47
     isKindOfClass
    0.45
     [_
    0.44
     tutorial
    0.44
     decontamination
    0.43
     aerobics
    0.43
     lowers
    0.42
    POSITIVE LOGITS
    LE
    0.47
    Binding
    0.44
    LM
    0.44
    Heat
    0.42
    ｌ
    0.42
    Motivation
    0.42
    Pittsburgh
    0.41
    Climate
    0.40
    木
    0.40
     ہوئی۔
    0.40
    Activations Density 0.010%

    No Known Activations