© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79194
    Prev
    Next
    INDEX
    Explanations

    growing pains and future uncertainty

    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_31_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
     boj
    0.39
    reth
    0.37
    หัว
    0.37
    啈
    0.37
    QN
    0.36
    เด็ก
    0.35
    ontium
    0.35
     ভাগ্যবান
    0.35
    firstChild
    0.34
    reto
    0.34
    POSITIVE LOGITS
     ))}
    0.41
    দ্ম
    0.37
    odrome
    0.37
     antif
    0.37
     interconnection
    0.36
     momentum
    0.36
    }}}
    0.36
     طی
    0.36
    tugraz
    0.36
     strides
    0.35
    Activations Density 0.011%

    No Known Activations