© 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. 13568
    Prev
    Next
    INDEX
    Explanations

    grammatical constructs using pronouns such as 'he', 'it', 'they' along with words related to causation or expression.

    oai_token-act-pair · gemini-2.0-flash

    say "com" words

    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
     arrived
    -1.16
     arrives
    -1.14
    come
    -1.14
    Came
    -1.13
     came
    -1.10
    came
    -1.09
    Come
    -1.09
     Came
    -1.08
     CAME
    -1.07
    arrived
    -1.06
    POSITIVE LOGITS
     com
    1.16
    com
    1.04
    Com
    0.89
     Com
    0.88
    COM
    0.86
     COM
    0.69
     Coen
    0.66
    kom
    0.66
    comm
    0.66
    "}")
    0.65
    Activations Density 0.905%

    No Known Activations