© 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. 12972
    Prev
    Next
    INDEX
    Explanations

    mentions the country Somalia and nearby words "and", "in", "parts of"

    oai_token-act-pair · gemini-2.0-flash

    Geography and conflict

    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
    ########.
    -0.68
    enumii
    -0.66
    EndGlobalSection
    -0.63
    Попис
    -0.60
    scriptcase
    -0.58
     Rump
    -0.56
     SAI
    -0.55
    suke
    -0.55
    ArgsConstructor
    -0.54
    errHandler
    -0.54
    POSITIVE LOGITS
     estimés
    0.55
    ærke
    0.45
    NameInMap
    0.44
    REET
    0.44
     menta
    0.42
    GEBURTSDATUM
    0.42
     calendriers
    0.41
    })();
    0.40
    yard
    0.40
     indi
    0.40
    Activations Density 0.665%

    No Known Activations