INDEX

Explanations

text about stories

oai_token-act-pair · gemini-2.0-flash

Media descriptions/reviews

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resourceCulture

-0.82

 pleaſure

-0.73

 myſelf

-0.68

 ſeveral

-0.66

 houſe

-0.65

 ſever

-0.65

 ſhe

-0.64

 themſelves

-0.63

Hauptartikel

-0.63

 Reſ

-0.63

POSITIVE LOGITS

PreferredItem

0.58

hoeddwyd

0.57

 autorytatywna

0.47

原始内容存档于

0.46

IRUS

0.45

 onPostExecute

0.45

iastes

0.45

بوابة

0.44

ToBounds

0.44

ној

0.43

Activations Density 0.734%

text about stories

Media descriptions/reviews

No Comments

No Known Activations