© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7958
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly in Germany and surrounding areas and transportation hubs

    oai_token-act-pair · gemini-2.0-flash

    French words

    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
    #+#
    -0.75
    EndInit
    -0.73
     متعلقه
    -0.65
    oneofs
    -0.64
    abestanden
    -0.64
     Etr
    -0.60
     propOrder
    -0.59
    AnchorStyles
    -0.57
    tvguidetime
    -0.56
    DockStyle
    -0.56
    POSITIVE LOGITS
     fumée
    0.69
     volontaire
    0.62
     poussière
    0.57
     chrétiens
    0.56
     noires
    0.56
     spéciale
    0.55
     rêves
    0.54
     refroid
    0.54
    heit
    0.54
     végétale
    0.54
    Activations Density 3.728%

    No Known Activations