© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13098
    Prev
    Next
    INDEX
    Explanations

    mostly short, common words that often connect phrases.

    oai_token-act-pair · gemini-2.0-flash

    User experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    paksa
    -0.53
    ariats
    -0.46
    TabLayout
    -0.46
    حياتها
    -0.45
    туга
    -0.44
     decidieron
    -0.43
     Act
    -0.43
    ball
    -0.42
    WebElementEntity
    -0.42
    early
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.76
    PDOException
    0.70
    awakeFromNib
    0.66
     })}
    0.66
    ftagPool
    0.65
    رشف
    0.65
    脚注の使い方
    0.63
     IBOutlet
    0.61
    "])
    0.60
    帖最后由
    0.60
    Activations Density 3.603%

    No Known Activations