INDEX

Explanations

descriptions of processes involving physical manipulation or movement, especially with tools or body parts.

oai_token-act-pair · gemini-2.0-flash

Paths and movement

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

MessageTagHelper

-0.69

InputTagHelper

-0.67

StoryboardSegue

-0.66

 SwitchCompat

-0.65

 دیکھیے

-0.65

DeleteBehavior

-0.65

MigrationBuilder

-0.63

 htons

-0.62

">—

-0.62

NamedQueries

-0.61

POSITIVE LOGITS

 path

0.60



0.57

 Path

0.53

 across

0.52

path

0.52

 passed

0.51

Path

0.49

划

0.48

кура

0.48

 move

0.47

Activations Density 2.013%

descriptions of processes involving physical manipulation or movement, especially with tools or body parts.

Paths and movement

No Comments

No Known Activations