© 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. 157817
    Prev
    Next
    INDEX
    Explanations

    in *Klebsiella* and *Haemophilus*

    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
    <0x0D>
    1.62
    н
    1.29
    т
    1.24
    ى
    1.20
     powied
    1.15
    м
    1.14
    </strong>
    1.13
    </em>
    1.13
    n
    1.12
    تي
    1.10
    POSITIVE LOGITS
     piezoelectric
    1.21
     cationic
    1.20
     collecting
    1.15
     malicious
    1.14
    )
    1.14
     in
    1.13
     gasoline
    1.13
    یده
    1.09
     mitigating
    1.09
     viscosity
    1.07
    Activations Density 0.000%

    No Known Activations