© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80943
    Prev
    Next
    INDEX
    Explanations

    wasted time or effort

    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_0_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
    -
    2.13
    )
    1.98
    1.60
    ون
    1.58
    }
    1.53
    ie
    1.48
    >
    1.45
    ب
    1.34
    (
    1.34
    x
    1.31
    POSITIVE LOGITS
    ла
    1.43
     is
    1.37
    un
    1.24
    ta
    1.24
    time
    1.23
    tx
    1.21
    ᾗ
    1.21
    tw
    1.17
    𝘨
    1.16
    tic
    1.14
    Activations Density 0.000%

    No Known Activations