INDEX

Explanations

the preposition "in" and words that often appear near it such as "part" and sometimes "or"

oai_token-act-pair · 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

 Parts

-2.78

Parts

-2.73

parts

-2.73

 parts

-2.70

 PARTS

-2.42

PARTS

-2.30

 partes

-2.13

Part

-2.11

 Part

-2.08

PART

-1.93

POSITIVE LOGITS

(!__

0.67

 large

0.65

ScopeManager

0.57

ynchrotron

0.57

large

0.57

AxisAlignment

0.55

 الرياضيه

0.53

XmlEnum

0.53

ksikon

0.52

 Large

0.49

Activations Density 4.421%

the preposition "in" and words that often appear near it such as "part" and sometimes "or"

No Comments

No Known Activations