INDEX

Explanations

mentions or instances of something existing, being located, or presented in a certain way.

oai_token-act-pair · gemini-2.0-flash

exist

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

thun

-0.51

coming

-0.50

hold

-0.47

taken

-0.46

)");

-0.45

 قسم

-0.45

 present

-0.45

lacht

-0.45

acionales

-0.45

Становништво

-0.45

POSITIVE LOGITS

 disambiguazione

0.88

richTextPanel

0.77

הערות

0.77

EndGlobalSection

0.75

contentLoaded

0.72

ThroughAttribute

0.70

verwijspagina

0.70

OGND

0.69

tanleria

0.66

曖昧さ回避

0.66

Activations Density 4.316%

mentions or instances of something existing, being located, or presented in a certain way.

exist

No Comments

No Known Activations