© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83080
    Prev
    Next
    INDEX
    Explanations

    seems counterintuitive

    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_29_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
    ्मी
    0.45
    𝐁
    0.42
     мене
    0.41
     elekt
    0.39
    ॰
    0.38
    𝐌
    0.37
     ಏ
    0.37
    𝐋
    0.37
    Stat
    0.36
    μο
    0.36
    POSITIVE LOGITS
     there
    0.46
    !.
    0.42
     productive
    0.41
    anta
    0.40
     هناك
    0.40
    !<
    0.40
    malıdır
    0.39
    াতার
    0.39
    innam
    0.39
     bisogna
    0.38
    Activations Density 0.005%

    No Known Activations