INDEX

Explanations

many instances of quotation marks and references to online game content.

oai_token-act-pair · gemini-2.0-flash

online forum snippets

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

 виправивши

-0.66

 EconPapers

-0.66

expandindo

-0.59

PERATURE

-0.58

cipline

-0.58

 kaarangay

-0.56

hematical

-0.54

VIRONMENT

-0.53

 CURIAM

-0.53

Demografía

-0.52

POSITIVE LOGITS

TG

0.62

TP

0.59

TTT

0.56

SX

0.56

 kinda

0.56

 gonna

0.55

 👎

0.55

LoL

0.54

 Juve

0.54

TG

0.53

Activations Density 18.155%

many instances of quotation marks and references to online game content.

online forum snippets

No Comments

No Known Activations