© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13413
    Prev
    Next
    INDEX
    Explanations

    words associated with writing or creating, or things that commonly happen in a particular location, or an emphasized point

    oai_token-act-pair · gemini-2.0-flash

    General references

    np_max-act · gemini-2.0-flash

    place

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    I
    -0.51
     ability
    -0.47
     forward
    -0.46
     I
    -0.45
    â
    -0.42
     effective
    -0.42
     ef
    -0.42
     time
    -0.42
    ,
    -0.41
     match
    -0.41
    POSITIVE LOGITS
     يتيمه
    1.07
     Efq
    1.02
     '\\;'
    1.01
     препратки
    0.98
     resourceCulture
    0.96
    principalTable
    0.96
    extAlignment
    0.90
    HideFlags
    0.88
    IsContent
    0.87
    (!__
    0.86
    Activations Density 1.595%

    No Known Activations