© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173251
    Prev
    Next
    INDEX
    Explanations

    Indian film titles

    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_20_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
     gerne
    0.48
    kej
    0.47
     Tender
    0.45
     Reliance
    0.43
     Pulse
    0.42
    輒
    0.42
    wi
    0.42
    itecture
    0.41
    uli
    0.41
     Wi
    0.41
    POSITIVE LOGITS
     ارو
    0.48
    })(
    0.46
    知識
    0.46
    })+\
    0.44
    })^{-
    0.44
     pamo
    0.44
     enemigo
    0.43
     genoeg
    0.43
    }=[
    0.42
    aprend
    0.42
    Activations Density 0.001%

    No Known Activations