© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13118
    Prev
    Next
    INDEX
    Explanations

    text related to autobiographical and biographical information, especially personal anecdotes and family history

    oai_token-act-pair · gemini-2.0-flash

    autobiographical paragraphs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    '):
    -0.60
    "):
    -0.60
    ?')
    -0.58
     papy
    -0.56
    ICOLON
    -0.56
    niosek
    -0.56
     penetrates
    -0.56
     interdit
    -0.55
    حوالہ
    -0.55
    Източници
    -0.54
    POSITIVE LOGITS
    adpleegd
    0.65
    Personendaten
    0.59
     propOrder
    0.58
    LayoutConstraint
    0.57
    анта
    0.50
    Koordinaten
    0.47
    lence
    0.47
    mybatisplus
    0.46
    centerY
    0.45
    lav
    0.45
    Activations Density 6.257%

    No Known Activations