INDEX

Explanations

mentions of days, attacks and official political discourse

oai_token-act-pair · gemini-2.0-flash

days and events

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 beginnetje

-0.85

ViewChild

-0.73

 مواليد

-0.71

Autoritní

-0.70

esez

-0.69

ContentAsync

-0.68

سطس

-0.67

IVEREF

-0.67

ArrowToggle

-0.67

__":

-0.66

POSITIVE LOGITS

ExceptionHandler

0.52

IfNot

0.44

はじめに

0.44

 tiêu

0.43

rq

0.43

 expo

0.43

SHUT

0.41

 tenu

0.39

rub

0.39

ến

0.38

Activations Density 32.208%

mentions of days, attacks and official political discourse

days and events

No Comments

No Known Activations