© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5462
    Prev
    Next
    INDEX
    Explanations

    pronouns being used by a speaker and often in conjunction with the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    il

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     utafitiHapana
    -0.72
    istoitu
    -0.64
     photolibrary
    -0.63
     فريبيس
    -0.63
     aient
    -0.60
     invokingState
    -0.59
     ་་
    -0.59
    󠁴
    -0.57
     étions
    -0.57
    ########.
    -0.57
    POSITIVE LOGITS
     y
    0.59
     s
    0.52
    EndContext
    0.51
     n
    0.49
     S
    0.48
     prie
    0.45
     ne
    0.45
     me
    0.44
     Might
    0.44
     man
    0.43
    Activations Density 0.444%

    No Known Activations