© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11477
    Prev
    Next
    INDEX
    Explanations

    expressions of time and location

    oai_token-act-pair · gemini-2.0-flash

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    __":
    -0.81
    __":
    -0.81
    Hochspringen
    -0.76
    Tikang
    -0.74
    LookAnd
    -0.71
    httphttps
    -0.70
     ویکی‌پدی
    -0.70
    __':
    -0.69
    esModule
    -0.67
    +#+#
    -0.66
    POSITIVE LOGITS
    virons
    0.52
    Expedia
    0.51
     Leader
    0.46
    convergence
    0.46
     wrong
    0.45
    ⓘ
    0.45
    rxjs
    0.45
    baik
    0.45
    jona
    0.44
    Scholars
    0.44
    Activations Density 0.948%

    No Known Activations