INDEX

Explanations

the word "stretch"

oai_token-act-pair · gemini-2.0-flash

stretch

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-2.66

Efq

-2.59

 myſelf

-2.44

 Monfieur

-2.34

 Jefus

-2.33

 Majefty

-2.31

 raiſ

-2.25

 Reſ

-2.19

 ſeveral

-2.17

 Theſe

-2.17

POSITIVE LOGITS

1.43

1.11

1.04

0.99

0.98

0.97

0.96

Activations Density 0.339%

the word "stretch"

stretch

No Comments

No Known Activations