INDEX

Explanations

numbers (especially percentages and quantities) in the text

oai_token-act-pair · gemini-2.0-flash

Percentages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

WriteBarrier

-0.86

 pleaſure

-0.82

 متعلقه

-0.82

AddTagHelper

-0.81

expandindo

-0.72

 purpoſe

-0.72

 houſe

-0.71

LookAnd

-0.71

الحياه

-0.70

ſelf

-0.69

POSITIVE LOGITS

 referenties

0.55

Band

0.54

 nyata

0.52

än

0.49

endaftaran

0.49

 Band

0.48

bebasan

0.46

tracks

0.46

 tunggal

0.46

 kreatif

0.45

Activations Density 3.757%

numbers (especially percentages and quantities) in the text

Percentages

No Comments

No Known Activations