© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213893
    Prev
    Next
    INDEX
    Explanations

    plant stems or music stems

    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_5_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
    。
    1.53
    .
    1.52
    ।
    1.39
    ]
    1.09
    ۔
    1.08
    Ла
    1.07
     savory
    1.06
    Но
    1.02
    Что
    1.00
    На
    0.99
    POSITIVE LOGITS
    he
    1.40
    is
    1.39
    é
    1.24
     and
    1.20
    ко
    1.20
    ли
    1.19
     as
    1.16
    т
    1.16
    هم
    1.14
    baixo
    1.14
    Activations Density 0.002%

    No Known Activations