INDEX

Explanations

character information and plot points in book or movie summaries.

oai_token-act-pair · gemini-2.0-flash

Action verbs

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

 AssemblyCompany

-0.93

 BoxFit

-0.67

 actionMode

-0.66

κίνη

-0.64

 Offisielt

-0.64

 AssemblyTitle

-0.63

 overtook

-0.63

WriteAttribute

-0.63

 wonen

-0.61

หวัด

-0.61

POSITIVE LOGITS

 begins

0.79

 becomes

0.79

 starts

0.77

 decides

0.73

 develops

0.73

 gets

0.72

 settles

0.71

 comes

0.68

 discovers

0.68

 takes

0.66

Activations Density 2.283%

character information and plot points in book or movie summaries.

Action verbs

No Comments

No Known Activations