© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20225
    Prev
    Next
    INDEX
    Explanations

    AddITION

    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_56_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
     coi
    0.34
     plunging
    0.34
    ismuth
    0.33
    ônico
    0.33
    ウザ
    0.33
    Cached
    0.33
    一大
    0.32
    戚
    0.32
    SKI
    0.31
    issent
    0.31
    POSITIVE LOGITS
     Add
    1.73
     add
    1.71
     Addition
    1.60
     addition
    1.59
    add
    1.56
    Add
    1.56
     adição
    1.38
     adicion
    1.37
    Addition
    1.37
    ADD
    1.36
    Activations Density 0.007%

    No Known Activations