© 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. 12889
    Prev
    Next
    INDEX
    Explanations

    instances of people going somewhere or doing something to a great degree

    oai_token-act-pair · gemini-2.0-flash

    unusual or uncommon words

    np_token-act-pair-logits · gpt-4o-mini

    go

    np_max-act-logits · gemini-2.0-flash
    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
    脚注の使い方
    -0.65
    RegressionTest
    -0.65
    didSet
    -0.64
     "..\..\..\
    -0.63
    posedge
    -0.63
     JpaRepository
    -0.63
    BeginContext
    -0.62
     bezeichneter
    -0.61
     disambiguazione
    -0.60
    })->
    -0.59
    POSITIVE LOGITS
     Hälfte
    0.49
     détach
    0.47
     électroniques
    0.46
     hamstring
    0.45
     Ceramby
    0.44
     hayvan
    0.44
     Infórmanos
    0.42
     hvem
    0.42
     Krieges
    0.42
     supérieurs
    0.41
    Activations Density 0.320%

    No Known Activations