© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4275
    Prev
    Next
    INDEX
    Explanations

    words and prefixes with 'co-' and 'micro-'

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to computational or scientific contexts

    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
     ModelExpression
    -0.66
    IsContent
    -0.66
    AddTagHelper
    -0.66
    /*---
    -0.56
    ur
    -0.56
     CreateTagHelper
    -0.56
    unding
    -0.55
    opsida
    -0.53
     ProtoMessage
    -0.52
     betweenstory
    -0.52
    POSITIVE LOGITS
    DECREF
    0.49
    évaluateur
    0.47
    ecore
    0.46
     calendriers
    0.44
     khăn
    0.44
     dàng
    0.43
    cett
    0.43
    醐
    0.42
    ennia
    0.42
     full
    0.41
    Activations Density 1.043%

    No Known Activations