INDEX

Explanations

articles that are followed by nouns or the preposition "to"

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_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mascul

-0.54

 masculina

-0.53

BagConstraints

-0.53

 Democrá

-0.53

 feminina

-0.51

𓃵

-0.50

Jegyzetek

-0.49

 Tenor

-0.49

or

-0.49

 Demok

-0.49

POSITIVE LOGITS

TintMode

0.61

uxxxx

0.59

principalColumn

0.58

parsedMessage

0.54

TagHelper

0.54

mine

0.50

0.49

 يتيمه

0.49

TabIndex

0.49

 користу

0.49

Activations Density 2.239%

articles that are followed by nouns or the preposition "to"

the

No Comments

No Known Activations