INDEX

Explanations

a variety of numbers, code snippets and special characters

oai_token-act-pair · gemini-2.0-flash

Math/code symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 (−

-1.16

(-

-1.11

$(-

-1.06

 freezing

-1.04

 Freezing

-1.02

(−

-1.02

$=-

-1.01

$[-

-1.01

 freeze

-0.96

 frozen

-0.95

POSITIVE LOGITS

 سكانية

0.46

 high

0.45

syk

0.45

 тур

0.42

ścio

0.41

itana

0.41

iosa

0.41

Fig

0.41

ApJ

0.41

kar

0.40

Activations Density 1.396%

a variety of numbers, code snippets and special characters

Math/code symbols

No Comments

No Known Activations