© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134933
    Prev
    Next
    INDEX
    Explanations

    gorilla ape primate

    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_37_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
    ]/*
    0.38
     tyr
    0.38
    cccs
    0.36
    ]//
    0.35
    oš
    0.35
     whanne
    0.35
     ол
    0.35
    ]))
    0.35
    ]<
    0.35
    ppings
    0.34
    POSITIVE LOGITS
     chimpan
    1.07
     ape
    1.05
     primate
    1.02
     gorilla
    1.01
     apes
    0.99
     Ape
    0.90
     gorillas
    0.88
     primates
    0.84
     Gorilla
    0.84
    🦍
    0.75
    Activations Density 0.003%

    No Known Activations