INDEX

Explanations

short descriptions followed by summaries and keywords

oai_token-act-pair · gemini-2.0-flash

Short stories/descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 short

-1.41

short

-1.35

Short

-1.27

 Short

-1.27

 SHORT

-1.15

SHORT

-1.11

 pendek

-1.01

 kurze

-0.99

 shorts

-0.98

 shorter

-0.98

POSITIVE LOGITS

EDEFAULT

0.65

TagMode

0.62

 estekak

0.60

DockStyle

0.59

 utafiti

0.58

 PicClick

0.57

})`

0.55

 disambiguazione

0.55

 newOwner

0.54

 Familienname

0.53

Activations Density 19.149%

short descriptions followed by summaries and keywords

Short stories/descriptions

No Comments

No Known Activations