INDEX

Explanations

text related to travel destinations and recommendations

oai_token-act-pair · gemini-2.0-flash

reviews

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

SharedDtor

-0.69

 Mechanism

-0.65

 &___

-0.65

 leadership

-0.60

expandindo

-0.60

 Technician

-0.59

 Leadership

-0.59

 Mechan

-0.59

 Manipulation

-0.59

CppCodeGen

-0.58

POSITIVE LOGITS

 Normdatei

0.47

ocino

0.45

 sunsets

0.43

homonymie

0.43

enumi

0.42

copyWith

0.41

rovnik

0.41

 cottage

0.41

 cottages

0.41

achios

0.40

Activations Density 18.682%

text related to travel destinations and recommendations

reviews

No Comments

No Known Activations