© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3069
    Prev
    Next
    INDEX
    Explanations

    words relating to crime, police investigations, potential abuse, and bureaucracy.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    SupportActionBar
    -0.65
     Efq
    -0.60
    teness
    -0.57
    <_>
    -0.57
     jemals
    -0.57
    SharedDtor
    -0.56
     aDecoder
    -0.56
     extant
    -0.56
    зец
    -0.55
     közül
    -0.55
    POSITIVE LOGITS
    tvguidetime
    0.56
    rungsseite
    0.48
    key
    0.48
    lexia
    0.47
     disambiguazione
    0.44
     bên
    0.43
    handel
    0.43
    amis
    0.43
    rifuge
    0.43
    rolid
    0.43
    Activations Density 6.171%

    No Known Activations