© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13688
    Prev
    Next
    INDEX
    Explanations

    mentions of physical locations, especially capitalized ones that could be states or regions

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Channel
    -0.76
     Circle
    -0.76
     Road
    -0.75
     Valley
    -0.75
     River
    -0.75
     Room
    -0.74
     LANE
    -0.74
     RIVER
    -0.73
     Lane
    -0.73
     Island
    -0.73
    POSITIVE LOGITS
    __':
    0.54
    __":
    0.49
    <!--[
    0.48
     endwhile
    0.44
    })`
    0.44
    })();
    0.43
    )['
    0.42
    endwhile
    0.42
    SaveChangesAsync
    0.42
    noinspection
    0.41
    Activations Density 3.199%

    No Known Activations