© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2988
    Prev
    Next
    INDEX
    Explanations

    capitalized words, words representing numbers or quantities, and words referring to locking/blocking threads

    oai_token-act-pair · gemini-2.0-flash

    Code and logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     offered
    -1.29
     made
    -1.27
     created
    -1.26
     produced
    -1.22
     presented
    -1.22
     received
    -1.22
     claimed
    -1.19
     designed
    -1.18
     submitted
    -1.18
     prepared
    -1.16
    POSITIVE LOGITS
    ajoz
    0.48
     exit
    0.43
     how
    0.43
     defense
    0.43
     enduro
    0.42
     intermission
    0.41
     fairness
    0.41
     defenses
    0.41
    autaire
    0.41
     varanda
    0.41
    Activations Density 4.662%

    No Known Activations