© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161405
    Prev
    Next
    INDEX
    Explanations

    hitting the key points

    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_2_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
    1.99
    。「
    1.27
    ta
    1.27
    ي
    1.19
    tan
    1.16
    d
    1.13
    、
    1.12
    tu
    1.08
    ll
    1.06
    l
    1.03
    POSITIVE LOGITS
    ла
    1.26
    "
    1.25
    ัน
    1.23
    ۹
    1.17
    (
    1.07
    ർ
    1.05
    ки
    1.03
    я
    1.00
    ".
    1.00
    ian
    0.99
    Activations Density 0.001%

    No Known Activations