© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206669
    Prev
    Next
    INDEX
    Explanations

    microSD cards

    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_19_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
     কতক
    0.45
    थित
    0.45
     терми
    0.44
     avenge
    0.43
     expedite
    0.43
     কোম্পানি
    0.42
    堷
    0.42
     affirmatively
    0.42
    摡
    0.41
     compagnies
    0.41
    POSITIVE LOGITS
     series
    0.53
    Series
    0.51
    inander
    0.48
     Series
    0.48
    Enhanced
    0.46
    Serialized
    0.45
    Newline
    0.45
     enhancement
    0.44
    series
    0.44
    Enh
    0.44
    Activations Density 0.001%

    No Known Activations