© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206063
    Prev
    Next
    INDEX
    Explanations

    calling or referring to

    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_20_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
     ilişkin
    0.36
     précédents
    0.36
     linkedin
    0.33
    ณ
    0.33
     opio
    0.32
     LinkedIn
    0.32
    μοσ
    0.32
     Fiscal
    0.32
    ంద్
    0.32
    麹
    0.32
    POSITIVE LOGITS
     Medizin
    0.37
     bathtub
    0.35
    toilet
    0.35
    DEBUGFS
    0.33
    Kunst
    0.33
    ారా
    0.33
    bathtub
    0.32
     looking
    0.31
    bath
    0.31
     உடை
    0.31
    Activations Density 0.004%

    No Known Activations