© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14057
    Prev
    Next
    INDEX
    Explanations

    the number 8, sometimes in the context of the year 1980 or the US legal code

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     pinulongan
    -1.16
     transfieras
    -1.13
     nahilalakip
    -1.13
    曖昧さ回避
    -1.06
    LookAnd
    -1.05
    ]--;
    -1.03
     оригіналу
    -1.00
    ⓧ
    -1.00
    UnusedPrivate
    -1.00
    SourceChecksum
    -0.98
    POSITIVE LOGITS
    2
    0.83
    5
    0.68
    3
    0.66
    1
    0.66
    4
    0.60
    th
    0.55
    6
    0.55
    0
    0.54
    9
    0.50
    S
    0.48
    Activations Density 7.797%

    No Known Activations