INDEX

Explanations

javascript code

oai_token-act-pair · gemini-2.0-flash

code errors/exceptions

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

yn

-0.47

onto

-0.46

եռ

-0.46

ix

-0.45

 permitan

-0.44

user

-0.44

echos

-0.43

acia

-0.43

øn

-0.43

 genome

-0.43

POSITIVE LOGITS

tagHelperRunner

1.02

httphttps

0.78

UnusedPrivate

0.74

Хьажоргаш

0.72

tanleria

0.71

 Roskov

0.70

цездатний

0.69

喱

0.67

 виправивши

0.63

 BorderSide

0.62

Activations Density 0.481%

javascript code

code errors/exceptions

No Comments

No Known Activations