© 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. 10611
    Prev
    Next
    INDEX
    Explanations

    text where the letter L is followed by a period

    oai_token-act-pair · gemini-2.0-flash

    Los Angeles

    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
    oa̍t
    -0.65
    "]));
    -0.65
    __':
    -0.60
    Personendaten
    -0.59
    revalidate
    -0.56
    ']):
    -0.54
    MigrationBuilder
    -0.53
    XmlAccessType
    -0.53
    lioz
    -0.53
    //}
    -0.52
    POSITIVE LOGITS
     الاطلاع
    0.47
    이션
    0.45
    ulus
    0.45
    IGI
    0.44
    ITTER
    0.44
    OPE
    0.44
    urio
    0.43
    derna
    0.43
    pdo
    0.42
    ULUS
    0.42
    Activations Density 3.388%

    No Known Activations