INDEX

Explanations

unicode whitespace characters.

oai_token-act-pair · gemini-2.0-flash

whitespace

np_max-act · 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

Negative Logits

Efq

-1.12

 myſelf

-1.11

 pleaſure

-1.06

 Monfieur

-1.06

 purpoſe

-1.01

 Shakspeare

-1.01

 anſ

-1.00

 ſtate

-1.00

 preſent

-0.97

 foncé

-0.97

POSITIVE LOGITS

ьаж

0.73

tagHelper

0.71

RegressionTest

0.66

Tam

0.65

)))),

0.65

usehen

0.65

 surla

0.65

cum

0.64

the

0.63

="../../

0.63

Activations Density 2.290%

unicode whitespace characters.

whitespace

No Known Activations