© 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. 202613
    Prev
    Next
    INDEX
    Explanations

    calibers and ammunition

    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
    I
    0.23
    Bj
    0.21
    It
    0.21
    AY
    0.20
    Gust
    0.20
    ोग्रा
    0.20
     It
    0.20
    വിടെ
    0.20
    irthday
    0.20
     പരിച
    0.20
    POSITIVE LOGITS
    ِيم
    0.20
    ียม
    0.19
    బు
    0.19
     باوجود
    0.19
    جهة
    0.19
    碜
    0.19
     oversaw
    0.18
    као
    0.18
     recompens
    0.18
    ̀u
    0.18
    Activations Density 0.000%

    No Known Activations