INDEX

Explanations

words related to problem solving and providing information

oai_token-act-pair · gemini-2.0-flash

Desires and intentions

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

 CreateTagHelper

-0.84

LookAnd

-0.75



-0.73

 للمعارف

-0.72

 nahilalakip

-0.70

LabelTagHelper

-0.70

exitRule

-0.68

 comigo

-0.67

 conmigo

-0.66

 متعلقه

-0.66

POSITIVE LOGITS

":

0.50

Form

0.45

hed

0.44

NodeId

0.43

 Pred

0.43

henko

0.42

"]:

0.40

త్ర

0.40

?',

0.39

Slo

0.39

Activations Density 33.238%

words related to problem solving and providing information

Desires and intentions

No Comments

No Known Activations