© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140347
    Prev
    Next
    INDEX
    Explanations

    counterfactual explanations

    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_12_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
     recuerda
    0.51
     MILLER
    0.45
     Lewis
    0.44
     CEO
    0.44
    ҥ
    0.43
     conceding
    0.43
     avuto
    0.42
     malice
    0.42
     LEWIS
    0.42
     concess
    0.42
    POSITIVE LOGITS
    sa
    0.48
    jakarta
    0.44
    Universität
    0.43
    Slim
    0.43
    f
    0.43
    OL
    0.43
    Cafe
    0.43
    alloween
    0.42
    Health
    0.42
    Er
    0.41
    Activations Density 0.001%

    No Known Activations