INDEX

Explanations

mentions of "the" followed by a noun describing a body or society

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 للمعارف

-0.88

IntoConstraints

-0.77

الحياه

-0.67

IVEREF

-0.65

HtmlAttribute

-0.65

 utafitiHapana

-0.65

цездатний

-0.62

]")]

-0.60

COUVER

-0.56

rlpool

-0.55

POSITIVE LOGITS

 arrep

0.49

ORUM

0.49

 tvrd

0.48

TypeMap

0.47

/**

0.47

 sobě

0.47

行政区划

0.47

ństw

0.45

schod

0.44

bildeten

0.44

Activations Density 6.217%

mentions of "the" followed by a noun describing a body or society

the

No Comments

No Known Activations