INDEX

Explanations

capitalized words and the substring "He"

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-0.77

$.

-0.75

giveness

-0.74

BibitemShut

-0.74

 ſeveral

-0.69

 kasarigan

-0.66

resaid

-0.66

 canary

-0.65

 utafitiHapana

-0.65

 myſelf

-0.65

POSITIVE LOGITS

<eos>

0.80

0.75

0.63

Portály

0.60

<bos>

0.60

’

0.58

0.55

Transkript

0.53

0.52

🎰

0.52

Activations Density 1.805%

capitalized words and the substring "He"

No Comments

No Known Activations