© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7877
    Prev
    Next
    INDEX
    Explanations

    location names or administrative divisions

    oai_token-act-pair · gemini-2.0-flash

    words related to places and locations in Bosnia

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     HasFactory
    -0.70
    FormTagHelper
    -0.56
    styleType
    -0.54
    حوالہ
    -0.54
     nonatomic
    -0.53
    انيف
    -0.53
    atrième
    -0.53
    ัติ
    -0.52
    RegistryLite
    -0.52
     Rewrite
    -0.50
    POSITIVE LOGITS
     MonoBehaviour
    0.54
    ']))
    0.50
    skog
    0.49
    enumi
    0.47
    )$/,
    0.47
    VideoCapture
    0.47
    lix
    0.46
    RetentionPolicy
    0.46
    liet
    0.46
     gedaan
    0.45
    Activations Density 0.426%

    No Known Activations