© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166894
    Prev
    Next
    INDEX
    Explanations

    -

    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
     tenth
    0.37
    例文
    0.37
     halts
    0.37
     intent
    0.36
     nail
    0.35
     _$_
    0.34
    ține
    0.34
     veze
    0.34
     thrilling
    0.34
    Defaults
    0.34
    POSITIVE LOGITS
    db
    0.37
    over
    0.36
    SIL
    0.35
    UP
    0.35
     屋
    0.34
    Kod
    0.34
    ON
    0.34
    Sil
    0.34
    ルの
    0.34
    ары
    0.34
    Activations Density 0.002%

    No Known Activations