© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10990
    Prev
    Next
    INDEX
    Explanations

    Famous names, often followed by names or identifiers

    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_13_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
     feared
    0.22
    uoj
    0.22
    ških
    0.22
    汜
    0.22
     Hj
    0.21
     tracers
    0.21
    𝖘
    0.21
     therapists
    0.21
    œurs
    0.21
     처
    0.21
    POSITIVE LOGITS
    یا
    0.29
    ya
    0.27
    ia
    0.26
     temperatur
    0.26
    al
    0.26
    ata
    0.25
    نا
    0.24
    aka
    0.23
     Alabama
    0.23
    ion
    0.23
    Activations Density 0.053%

    No Known Activations