© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3312
    Prev
    Next
    INDEX
    Explanations

    references to a specific political organization in Bangladesh

    oai_token-act-pair · gemini-2.0-flash

    Bangladesh 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.97
    DockStyle
    -0.72
    醐
    -0.68
     estekak
    -0.66
    Rhestr
    -0.65
    HasOne
    -0.64
     متعلقه
    -0.63
     overheating
    -0.63
     tartalomajánló
    -0.61
    setof
    -0.60
    POSITIVE LOGITS
    Bar
    0.51
    baran
    0.50
     Bar
    0.49
    Bir
    0.47
     Bir
    0.47
    JEL
    0.46
    Ál
    0.46
    slo
    0.44
    selector
    0.44
     bar
    0.44
    Activations Density 0.422%

    No Known Activations